
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
from pandas.plotting import scatter_matrix


full_df = pd.read_csv('./airbnb-listings-extract.csv', sep=';', decimal='.')

# Filtrar por país (España) y crear una copia independiente
data_spain = full_df[full_df['Country Code'] == 'ES'].copy()


def is_madrid(location):
    madrid_areas = ['madrid', 'pozuelo', 'boadilla del monte', 'aravaca', 'las matas', 'san fernando de henares', 'ventas', 'chueca', 'vallecas', 'villa verde', 'delicias']
    if isinstance(location, str) and any(area in location.lower() for area in madrid_areas):
        return True
    return False

data_madrid = data_spain[data_spain['Smart Location'].apply(is_madrid)]


print(f"Valores únicos en 'Zipcode': {data_madrid['Zipcode'].unique()}")

Valores únicos en 'Zipcode': ['28007' '28001' '28006' '28009' '28028' '28002' '28016' nan '28046'
 '28039' '28020' '28025' '28041' '28026' '28019' '28018' '28053' '28038'
 '28030' '28010' '28003' '28035' '28008' '28013' '28034' '28040' '28023'
 '28011' '28024' '28044' '28021' '28031' '28032' '28037' '28042' '28224'
 '28017' '28027' '28043' '28033' '28050' '28045' '28012' '28005' '28014'
 '28036' '28004' '28029' '28015' '28105' '28051' '28022' '28055' '28054'
 '28047' '280013' '28094' '28002\n28002' '28850' '28660' '25008' '2015'
 '27004' '28060' '28056' '28290' '28049' '2805' '28052' '20013' '28048'
 '2815' '2802\n28012' 'Madrid 28004' '28830' '2804' '-' '28' '27013'
 '28058' '28051\n28051' '20126']


def clean_zipcode(zipcode):
    if pd.isna(zipcode) or not isinstance(zipcode, str):
        return None
    zipcode = zipcode.replace('Madrid', '').strip()
    zipcode = ''.join(filter(str.isdigit, zipcode)).split('\n')[0]
    return zipcode if zipcode.startswith('28') and len(zipcode) == 5 else None

data_madrid.loc[:, 'Zipcode'] = data_madrid['Zipcode'].apply(clean_zipcode)


from sklearn.model_selection import train_test_split

# Dividimos en Conjuntos de Entrenamiento y Prueba
train, test = train_test_split(data_madrid, test_size=0.2, shuffle=True, random_state=0)
print(f'Dimensiones del dataset de training: {train.shape}')
print(f'Dimensiones del dataset de test: {test.shape}')

# Guardamos
train.to_csv('./train.csv', sep=';', decimal='.', index=False)
test.to_csv('./test.csv', sep=';', decimal='.', index=False)

# Cargamos el dataset de train y trabajamos ÚNICAMENTE con él
data_train = pd.read_csv('./train.csv', sep=';', decimal='.')

Dimensiones del dataset de training: (10609, 89)
Dimensiones del dataset de test: (2653, 89)


pd.set_option('display.max_rows', None) # Configurar Pandas para mostrar todas las filas
pd.set_option('display.max_columns', None) # Configurar Pandas para mostrar todas las columnas


data_train.head().T


data_train.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 10609 entries, 0 to 10608
Data columns (total 89 columns):
 #   Column                          Non-Null Count  Dtype  
---  ------                          --------------  -----  
 0   ID                              10609 non-null  int64  
 1   Listing Url                     10609 non-null  object 
 2   Scrape ID                       10609 non-null  int64  
 3   Last Scraped                    10609 non-null  object 
 4   Name                            10609 non-null  object 
 5   Summary                         10223 non-null  object 
 6   Space                           7729 non-null   object 
 7   Description                     10605 non-null  object 
 8   Experiences Offered             10609 non-null  object 
 9   Neighborhood Overview           6645 non-null   object 
 10  Notes                           4036 non-null   object 
 11  Transit                         6617 non-null   object 
 12  Access                          6057 non-null   object 
 13  Interaction                     6055 non-null   object 
 14  House Rules                     6915 non-null   object 
 15  Thumbnail Url                   8624 non-null   object 
 16  Medium Url                      8624 non-null   object 
 17  Picture Url                     10595 non-null  object 
 18  XL Picture Url                  8624 non-null   object 
 19  Host ID                         10609 non-null  int64  
 20  Host URL                        10609 non-null  object 
 21  Host Name                       10607 non-null  object 
 22  Host Since                      10607 non-null  object 
 23  Host Location                   10580 non-null  object 
 24  Host About                      6623 non-null   object 
 25  Host Response Time              9292 non-null   object 
 26  Host Response Rate              9292 non-null   float64
 27  Host Acceptance Rate            0 non-null      float64
 28  Host Thumbnail Url              10607 non-null  object 
 29  Host Picture Url                10607 non-null  object 
 30  Host Neighbourhood              7986 non-null   object 
 31  Host Listings Count             10607 non-null  float64
 32  Host Total Listings Count       10607 non-null  float64
 33  Host Verifications              10604 non-null  object 
 34  Street                          10609 non-null  object 
 35  Neighbourhood                   7029 non-null   object 
 36  Neighbourhood Cleansed          10609 non-null  object 
 37  Neighbourhood Group Cleansed    10609 non-null  object 
 38  City                            10608 non-null  object 
 39  State                           10572 non-null  object 
 40  Zipcode                         10252 non-null  float64
 41  Market                          10568 non-null  object 
 42  Smart Location                  10609 non-null  object 
 43  Country Code                    10609 non-null  object 
 44  Country                         10609 non-null  object 
 45  Latitude                        10609 non-null  float64
 46  Longitude                       10609 non-null  float64
 47  Property Type                   10609 non-null  object 
 48  Room Type                       10609 non-null  object 
 49  Accommodates                    10609 non-null  int64  
 50  Bathrooms                       10571 non-null  float64
 51  Bedrooms                        10595 non-null  float64
 52  Beds                            10576 non-null  float64
 53  Bed Type                        10609 non-null  object 
 54  Amenities                       10528 non-null  object 
 55  Square Feet                     408 non-null    float64
 56  Price                           10601 non-null  float64
 57  Weekly Price                    2707 non-null   float64
 58  Monthly Price                   2660 non-null   float64
 59  Security Deposit                4538 non-null   float64
 60  Cleaning Fee                    6262 non-null   float64
 61  Guests Included                 10609 non-null  int64  
 62  Extra People                    10609 non-null  int64  
 63  Minimum Nights                  10609 non-null  int64  
 64  Maximum Nights                  10609 non-null  int64  
 65  Calendar Updated                10609 non-null  object 
 66  Has Availability                0 non-null      float64
 67  Availability 30                 10609 non-null  int64  
 68  Availability 60                 10609 non-null  int64  
 69  Availability 90                 10609 non-null  int64  
 70  Availability 365                10609 non-null  int64  
 71  Calendar last Scraped           10609 non-null  object 
 72  Number of Reviews               10609 non-null  int64  
 73  First Review                    8419 non-null   object 
 74  Last Review                     8418 non-null   object 
 75  Review Scores Rating            8325 non-null   float64
 76  Review Scores Accuracy          8312 non-null   float64
 77  Review Scores Cleanliness       8316 non-null   float64
 78  Review Scores Checkin           8302 non-null   float64
 79  Review Scores Communication     8314 non-null   float64
 80  Review Scores Location          8300 non-null   float64
 81  Review Scores Value             8299 non-null   float64
 82  License                         195 non-null    object 
 83  Jurisdiction Names              0 non-null      float64
 84  Cancellation Policy             10609 non-null  object 
 85  Calculated host listings count  10609 non-null  float64
 86  Reviews per Month               8419 non-null   float64
 87  Geolocation                     10609 non-null  object 
 88  Features                        10609 non-null  object 
dtypes: float64(27), int64(13), object(49)
memory usage: 7.2+ MB


data_train.describe()


missing_values = data_train.isnull().sum()

# Filtra las columnas que tienen valores faltantes, ordenados de mayor a menor
missing_values_filtered = missing_values[missing_values > 0].sort_values(ascending=True)
fig, ax = plt.subplots(figsize=(10, 14))

ax.barh(missing_values_filtered.index, missing_values_filtered.values, color='lightseagreen')

for s in ['top', 'bottom', 'left', 'right']:
    ax.spines[s].set_visible(False)

# Remove x, y Ticks
ax.xaxis.set_ticks_position('none')
ax.yaxis.set_ticks_position('none')

# Add padding between axes and labels
ax.xaxis.set_tick_params(pad=5)
ax.yaxis.set_tick_params(pad=5)

# Valor barra
for i in ax.patches:
    plt.text(i.get_width()+0.2, i.get_y()+0.5,
             str(round((i.get_width()), 2)),
             fontsize=10, fontweight='500',
             color='lightslategrey', va='center')
    
ax.set_title('Número de Valores Faltantes por Columna', fontsize=18, fontweight='500')
plt.show()


data_train.hist(bins=20, figsize=(24,16), color='teal')
plt.show()


# Calculamos la matriz de correlación para data_train
corr_matrix = data_train.select_dtypes(include=[np.number]).corr()

# Gráfico de calor para la matriz de correlación
plt.figure(figsize=(10, 8))
sns.heatmap(corr_matrix)
plt.title('Matriz de Correlación', fontsize=15)
plt.show()


# Gráfico de las correlaciones de la columna 'Price' con las demás
corr_with_price = corr_matrix["Price"].sort_values(ascending=False).drop('Price')  # Excluir la propia correlación de 'Price' con sí misma

plt.figure(figsize=(14, 10))
sns.barplot(x=corr_with_price.values, y=corr_with_price.index)
plt.title('Correlación con Price', fontsize=16)
plt.xlabel('Coeficiente de Correlación')
plt.ylabel('')
plt.show()


# Función para crear histogramas de múltiples columnas
def plot_histograms(df, columns, bins=20, color='royalblue', figsize=(20, 5)):
    fig, axs = plt.subplots(nrows=1, ncols=len(columns), figsize=figsize)

    # Asegura que axs sea un array, incluso con una sola columna
    if len(columns) == 1:
        axs = [axs]

    # Iterar a través de las columnas y los ejes para crear histogramas
    for col, ax in zip(columns, axs):
        df[col].dropna().hist(bins=bins, ax=ax, color=color)
        ax.set_title(col)
        ax.set_xlabel('Valor')
        ax.set_ylabel('Frecuencia')
        
        # Elimina la cuadrícula y los bordes
        ax.grid(False)
        for spine in ax.spines.values():
            spine.set_visible(False)

    plt.tight_layout()
    plt.show()


from pandas.plotting import scatter_matrix

# Función para crear una matriz de dispersión para atributos seleccionados
def plot_scatter_matrix(df, attributes, figsize=(14, 10), diagonal='kde',
                        color='royalblue', alpha=0.7, s=100, edgecolors='white',
                        suptitle='Matriz de Dispersión'):
   
    sns.set(style="whitegrid")
    scatter_matrix(df[attributes], figsize=figsize, diagonal=diagonal,
                   color=color, alpha=alpha, s=s, edgecolors=edgecolors)
    
    plt.suptitle(suptitle, size=16)
    plt.subplots_adjust(top=0.94, wspace=0.05, hspace=0.1)
    plt.show()


columns_to_include = ['Host ID', 'Host Response Rate', 'Host Listings Count', 'Host Total Listings Count']
plot_histograms(data_train, columns_to_include, bins=15, figsize=(20, 5))


print(data_train['Host Response Time'].value_counts())

Host Response Time
within an hour        5698
within a few hours    2168
within a day          1217
a few days or more     209
Name: count, dtype: int64


print(data_train['Host Listings Count'].describe())

count    10607.000000
mean         9.807674
std         27.624553
min          0.000000
25%          1.000000
50%          2.000000
75%          5.000000
max        265.000000
Name: Host Listings Count, dtype: float64


# Analizamos los registros que tienen un valor superior a 100 en 'Host Listings Count'
high_listing_hosts = data_train[data_train['Host Listings Count'] > 100]
host_counts = high_listing_hosts['Host Name'].value_counts()
print(f"Número de 'Host Name' únicos con más de 100 listados: {host_counts.shape[0]}")
print(f"Cantidad de veces que cada anfitrión aparece con más de 100 listados: {host_counts}")

# Agrupamos por "Host Name" y obtenemos el valor máximo de "Host Listings Count" para cada grupo
host_listings_max = high_listing_hosts.groupby('Host Name')['Host Listings Count'].max()
print(f"Valor máximo de cada {host_listings_max}")

Número de 'Host Name' únicos con más de 100 listados: 6
Cantidad de veces que cada anfitrión aparece con más de 100 listados: Host Name
Raquel          118
Erasmo´S         75
Spain Select     65
Javier           53
Teresa            3
Loic              1
Name: count, dtype: int64
Valor máximo de cada Host Name
Erasmo´S        114.0
Javier          207.0
Loic            265.0
Raquel          164.0
Spain Select    142.0
Teresa          136.0
Name: Host Listings Count, dtype: float64


# Correlación entre variables
columns_of_interest = ['Host ID', 'Host Total Listings Count','Host Listings Count','Host Response Rate','Price']
correlation_matrix = data_train[columns_of_interest].corr()

plt.figure(figsize=(5, 3))
sns.heatmap(correlation_matrix, annot=True, fmt=".2f", cmap='coolwarm', cbar=True)
plt.show()


# Gráfico de dispersión
attributes = ['Host ID', 'Host Listings Count', 'Host Response Rate', 'Price']
plot_scatter_matrix(data_train, attributes)


columns_to_include =['Latitude', 'Longitude' ,'Zipcode']
plot_histograms(data_train, columns_to_include, bins=15, figsize=(20, 5))


data_train[['City', 'State', 'Country Code', 'Country']].describe()


data_train[['Neighbourhood Cleansed', 'Neighbourhood Group Cleansed']].describe()


# Creamos un boxplot de precios por distrito
sns.set(style="whitegrid", palette="pastel")

plt.figure(figsize=(15, 7))
sns.boxplot(x='Neighbourhood Group Cleansed', y='Price', data=data_train, width=0.6, fliersize=5)

plt.title('Distribución de Precios por Distrito en Madrid', fontsize=16, weight=500)
plt.xlabel('Distrito', fontsize=14)
plt.ylabel('Precio', fontsize=14)
plt.xticks(rotation=90, ha='right')

sns.despine(trim=True)
plt.subplots_adjust(top=0.96)
plt.show()


np.random.seed(0)

def safe_mean(data):
    if len(data) == 0:
        return np.nan  # Retorna NaN si el conjunto está vacío
    return np.nanmean(data)  # Utiliza nanmean para ignorar los NaN en el cálculo

plt.figure(figsize=(10, 6))

hb = plt.hexbin(data_train['Longitude'], data_train['Latitude'], 
                C=data_train['Price'], gridsize=50, cmap='rocket_r', 
                reduce_C_function=safe_mean, edgecolors='none')

cb = plt.colorbar(hb, label='Precio medio por noche (€)')

plt.xlabel('Longitud', fontsize=12, fontweight='light')
plt.ylabel('Latitud', fontsize=12, fontweight='light')
plt.title('Mapa de calor de precios por noche en Madrid', fontsize=14, fontweight='500')

sns.despine(top=True, right=True, left=False, bottom=False)
plt.show()


correlation_matrix = data_train[['Latitude','Longitude','Zipcode','Price']].corr()
plt.figure(figsize=(5, 4))
sns.heatmap(correlation_matrix, annot=True, fmt=".2f", cmap='coolwarm', cbar=True)
plt.show()


columns_to_include = ['Accommodates','Bathrooms','Bedrooms','Beds','Square Feet']
plot_histograms(data_train, columns_to_include, bins=15, figsize=(24, 5))


sns.set(style="whitegrid")

fig, axes = plt.subplots(nrows=1, ncols=3, figsize=(20, 6))

# Gráfico de barras para 'Property Type'
data_train['Property Type'].value_counts().plot(kind='bar', color='darkslategray', ax=axes[0])
axes[0].set_title('Distribución de Tipos de Propiedades')
axes[0].set_xlabel('Tipo de Propiedad')
axes[0].set_ylabel('Frecuencia')
axes[0].tick_params(axis='x', rotation=90)

# Gráfico de barras para 'Room Type'
data_train['Room Type'].value_counts().plot(kind='bar', color='darkslategray', ax=axes[1])
axes[1].set_title('Distribución de Tipos de Habitaciones')
axes[1].set_xlabel('Tipo de Habitación')
axes[1].set_ylabel('Frecuencia')
axes[1].tick_params(axis='x', rotation=0) 

# Gráfico de barras para 'Bed Type'
data_train['Bed Type'].value_counts().plot(kind='bar', color='darkslategray', ax=axes[2])
axes[2].set_title('Distribución de Tipos de Cama')
axes[2].set_xlabel('Tipo de Cama')
axes[2].set_ylabel('Frecuencia')
axes[2].tick_params(axis='x', rotation=0)

sns.despine(trim=True)
plt.tight_layout()
plt.show()


sns.set_style("whitegrid") 
plt.figure(figsize=(16, 10))

# Gráfico de cajas para 'Property Type' y 'Price'
plt.subplot(1, 3, 1)
sns.boxplot(x='Property Type',y='Price',data=data_train,palette="magma",hue='Property Type',legend=False)
plt.xticks(rotation=45, ha='right') 
plt.title('Distribución de Precios por Tipo de Propiedad')
plt.xlabel('Tipo de Propiedad')
plt.ylabel('Precio')

# Gráfico de cajas para 'Room Type' y 'Price'
plt.subplot(1, 3, 2)
sns.boxplot(x='Room Type',y='Price',data=data_train,palette="magma",hue='Room Type',legend=False)
plt.xticks(rotation=45, ha='right')
plt.title('Distribución de Precios por Tipo de Habitación')
plt.xlabel('Tipo de Habitación')
plt.ylabel('Precio')

# Gráfico de cajas para 'Bed Type' y 'Price'
plt.subplot(1, 3, 3)
sns.boxplot(x='Bed Type',y='Price',data=data_train,palette="magma",hue='Bed Type',legend=False)
plt.xticks(rotation=45, ha='right')
plt.title('Distribución de Precios por Tipo de Cama')
plt.xlabel('Tipo de Cama')
plt.ylabel('Precio')

sns.despine(trim=True)
plt.tight_layout(pad=2)
plt.show()


# Scatter Plot
sns.set_style("whitegrid") 
g = sns.FacetGrid(data_train, col="Room Type", hue="Property Type", col_wrap=3, height=4)
g.map(sns.scatterplot, "Bedrooms", "Price")
g.add_legend()
plt.show()


# Scatter Plot
sns.set_style("whitegrid") 
g = sns.FacetGrid(data_train, col="Room Type", hue="Property Type", col_wrap=3, height=4)
g.map(sns.scatterplot, "Bathrooms", "Price")
g.add_legend()
plt.show()


# Pair Plot
sns.pairplot(data_train, hue="Room Type", 
             vars=["Price", "Bathrooms", "Bedrooms", "Beds"], 
             corner=True, palette="muted")
plt.show()


sns.set_style("whitegrid")
plt.figure(figsize=(15, 3))

plt.subplot(1, 3, 1)
sns.boxplot(data=data_train, x='Bathrooms', color="cornflowerblue")
plt.title('Distribución de Baños')

plt.subplot(1, 3, 2)
sns.boxplot(data=data_train, x='Bedrooms', color="cornflowerblue")
plt.title('Distribución de Dormitorios')

sns.despine(trim=True)

plt.subplot(1, 3, 3)
sns.boxplot(data=data_train, x='Beds', color="cornflowerblue")
plt.title('Distribución de Camas')

sns.despine(top=True, right=True, left=False, bottom=False)

plt.tight_layout()
plt.show()


sns.set_style("whitegrid")
plt.figure(figsize=(18, 8))

plt.subplot(1, 3, 1)
sns.boxplot(x='Bathrooms', y='Price', data=data_train, color="cornflowerblue")
plt.title('Distribución de Precios por Número de Baños')
plt.xlabel('Tipo de Propiedad')
plt.ylabel('Precio')

plt.subplot(1, 3, 2)
sns.boxplot(x='Bedrooms', y='Price', data=data_train, color="cornflowerblue")
plt.title('Distribución de Precios por Número de Dormitorios')
plt.xlabel('Tipo de Habitación')
plt.ylabel('Precio')

plt.subplot(1, 3, 3)
sns.boxplot(x='Beds', y='Price', data=data_train, color="cornflowerblue")
plt.title('Distribución de Precios por Número de Camas')
plt.xlabel('Tipo de Cama')
plt.ylabel('Precio')

sns.despine(trim=True)
plt.tight_layout()
plt.show()


print(f"Registros con 10 dormitorios:\n{data_train[data_train['Bedrooms'] == 10][['Bathrooms', 'Beds', 'Price', 'Property Type']]}")
print(f"\nRegistros con 0 dormitorios:\n{data_train[data_train['Bedrooms'] == 0][['Bathrooms', 'Beds', 'Price', 'Property Type']]}")
print(f"\nRegistros con 7 baños o más:\n{data_train[data_train['Bathrooms'] >= 7][['Bathrooms', 'Beds', 'Price', 'Property Type']]}")

Registros con 10 dormitorios:
      Bathrooms  Beds  Price    Property Type
82          6.0  16.0   40.0  Bed & Breakfast
1782        5.5   1.0   40.0            House
3859        6.0  16.0  180.0        Apartment
5557        6.5  16.0  850.0        Apartment
7916        0.0   2.0   39.0            House

Registros con 0 dormitorios:
       Bathrooms  Beds  Price       Property Type
42           1.0   1.0   60.0           Apartment
53           1.0   1.0   53.0           Apartment
77           1.0   2.0   66.0                Loft
126          1.0   3.0   55.0           Apartment
132          1.0   3.0   43.0  Serviced apartment
138          1.0   1.0  135.0           Apartment
142          1.0   2.0   69.0           Apartment
167          1.0   1.0   51.0           Apartment
170          1.0   1.0   59.0           Apartment
188          1.0   2.0   69.0           Apartment
192          1.0   1.0   69.0           Apartment
197          1.0   2.0  100.0                Loft
199          1.0   1.0   30.0           Apartment
227          1.0   1.0   50.0           Apartment
236          1.0   4.0   70.0           Apartment
242          1.0   2.0  100.0           Apartment
255          1.0   1.0   25.0           Apartment
307          1.0   1.0   45.0           Apartment
311          1.0   1.0   50.0         Condominium
320          1.0   2.0   60.0           Apartment
341          1.0   1.0   74.0           Apartment
346          1.0   1.0   40.0           Apartment
352          1.0   1.0   55.0           Apartment
366          1.0   1.0   59.0           Apartment
376          1.0   2.0   65.0           Apartment
404          1.0   1.0   70.0           Apartment
407          1.0   1.0   70.0           Apartment
446          1.0   2.0   66.0           Apartment
517          1.0   2.0   65.0           Apartment
553          1.0   2.0   50.0           Apartment
557          1.0   2.0   50.0               House
582          1.0   1.0   70.0           Apartment
595          1.0   1.0   35.0           Apartment
622          1.0   2.0   40.0           Apartment
623          1.0   1.0   60.0                Loft
636          1.0   2.0   64.0           Apartment
649          1.0   1.0   45.0           Apartment
671          1.0   1.0   35.0           Apartment
682          1.0   1.0   65.0                Loft
709          1.0   1.0   70.0           Apartment
716          1.0   2.0   75.0           Apartment
725          1.0   1.0   50.0           Apartment
730          1.0   1.0   29.0           Apartment
731          1.0   1.0   80.0           Apartment
748          1.0   1.0   45.0                Loft
784          2.0   3.0  133.0           Apartment
786          1.0   1.0   30.0           Apartment
791          1.0   1.0  115.0                Loft
804          1.0   2.0   59.0           Apartment
811          1.0   1.0   71.0           Apartment
822          1.0   1.0   57.0           Apartment
839          1.0   1.0   35.0           Apartment
859          1.0   1.0   60.0           Apartment
883          1.0   1.0   22.0                Loft
896          1.0   2.0   71.0           Apartment
904          1.0   2.0   47.0         Condominium
909          1.0   2.0   50.0           Apartment
918          1.0   1.0   60.0           Apartment
944          1.0   1.0   40.0           Apartment
964          1.0   1.0   80.0           Apartment
971          1.0   1.0   40.0           Apartment
976          1.0   1.0   13.0           Apartment
996          1.0   1.0   55.0           Apartment
1005         1.0   2.0   44.0                Loft
1026         1.0   1.0   58.0           Apartment
1027         1.0   1.0   55.0           Apartment
1043         1.0   1.0   65.0           Apartment
1060         1.0   1.0   30.0           Apartment
1063         1.0   2.0   50.0           Apartment
1085         1.0   1.0   60.0           Apartment
1118         1.0   2.0   76.0                Loft
1134         1.0   1.0   40.0           Apartment
1153         1.0   2.0   45.0           Apartment
1168         1.0   2.0   42.0           Apartment
1171         1.0   1.0   42.0           Apartment
1187         1.0   1.0   53.0           Apartment
1191         1.0   1.0   46.0           Apartment
1192         1.0   2.0   75.0           Apartment
1215         1.0   2.0   65.0           Apartment
1249         1.0   1.0   75.0           Apartment
1264         1.0   1.0   50.0           Apartment
1282         1.0   1.0  150.0           Apartment
1303         1.0   1.0   55.0           Apartment
1314         1.0   2.0   89.0           Apartment
1317         1.0   1.0   50.0                Loft
1332         1.0   1.0   76.0           Apartment
1333         1.0   1.0   35.0           Apartment
1370         1.0   1.0   49.0           Apartment
1383         1.0   2.0   40.0  Serviced apartment
1388         1.0   2.0   60.0           Apartment
1392         1.0   1.0   35.0           Apartment
1421         1.0   2.0   46.0           Apartment
1425         1.0   2.0   65.0                Loft
1427         1.0   1.0   28.0         Condominium
1429         1.0   2.0   65.0           Apartment
1435         1.0   2.0   45.0           Apartment
1458         1.0   2.0   50.0                Loft
1476         1.0   2.0   65.0           Apartment
1485         1.0   1.0   40.0         Condominium
1493         1.0   1.0   39.0           Apartment
1502         1.0   1.0   60.0           Apartment
1516         1.0   2.0   36.0           Apartment
1524         1.0   2.0   90.0           Apartment
1550         1.0   1.0   39.0           Apartment
1595         1.0   2.0   50.0           Apartment
1598         1.0   1.0   70.0           Apartment
1603         1.0   3.0   35.0           Apartment
1609         1.0   2.0   60.0                Loft
1635         1.0   1.0   70.0                Loft
1643         1.0   1.0   48.0           Apartment
1655         1.0   1.0   59.0           Apartment
1660         1.0   1.0   69.0           Apartment
1671         1.0   1.0  119.0           Apartment
1682         1.0   1.0   45.0           Apartment
1704         1.0   1.0   49.0           Apartment
1733         1.0   2.0   43.0           Apartment
1759         1.0   1.0   28.0           Apartment
1788         1.0   1.0   50.0           Apartment
1798         1.0   1.0   37.0           Apartment
1815         1.0   1.0   60.0           Apartment
1816         1.0   2.0   55.0           Apartment
1818         1.0   2.0   60.0           Apartment
1830         1.0   2.0   80.0           Apartment
1831         1.0   1.0   33.0           Apartment
1832         1.0   1.0   35.0         Condominium
1838         1.0   1.0   48.0           Apartment
1854         1.0   2.0   50.0           Apartment
1878         1.0   2.0   46.0           Apartment
1880         1.0   1.0   45.0                Loft
1885         1.0   2.0   75.0           Apartment
1890         1.0   1.0  109.0           Apartment
1897         1.0   4.0   55.0               Other
1902         1.0   1.0   31.0           Apartment
1918         1.0   1.0   40.0           Apartment
1929         1.0   1.0   40.0           Apartment
1941         1.0   1.0   30.0           Apartment
1944         1.0   1.0   80.0           Apartment
1957         1.0   2.0   72.0           Apartment
1978         1.0   1.0   49.0           Apartment
1985         1.0   2.0   45.0           Apartment
1996         1.0   1.0   40.0           Apartment
1997         1.0   2.0   42.0           Apartment
2027         1.0   1.0   85.0           Apartment
2033         1.0   1.0   43.0           Apartment
2058         1.0   1.0   60.0           Apartment
2066         1.0   1.0   45.0           Apartment
2072         1.0   2.0   65.0           Apartment
2075         1.0   1.0   49.0           Apartment
2084         1.0   1.0   60.0                Loft
2090         1.0   1.0   40.0           Apartment
2093         1.0   1.0   50.0                Loft
2095         1.0   2.0   95.0           Apartment
2142         1.0   1.0   55.0           Apartment
2167         1.0   1.0   32.0  Serviced apartment
2172         1.0   1.0   50.0           Apartment
2183         1.0   2.0   50.0           Apartment
2189         1.0   1.0   50.0           Apartment
2199         1.0   2.0  200.0           Apartment
2222         1.0   1.0   55.0           Apartment
2233         1.0   1.0   50.0           Apartment
2255         1.0   2.0   49.0           Apartment
2260         1.0   1.0   70.0           Apartment
2275         1.0   1.0   60.0           Apartment
2285         2.0   1.0   39.0           Apartment
2297         1.0   1.0   30.0           Apartment
2302         1.0   1.0   69.0           Apartment
2313         1.0   1.0   50.0                Loft
2315         1.0   2.0   50.0           Apartment
2330         1.0   1.0   60.0           Apartment
2343         1.0   2.0   50.0           Apartment
2344         1.0   2.0   70.0         Condominium
2356         1.0   1.0   47.0           Apartment
2380         1.0   2.0   53.0           Apartment
2382         1.0   1.0   60.0           Apartment
2407         1.0   1.0   70.0           Apartment
2420         1.0   2.0  125.0           Apartment
2426         1.0   1.0  525.0           Apartment
2439         1.0   1.0   48.0           Apartment
2465         1.0   2.0  100.0           Apartment
2488         1.0   2.0   29.0           Apartment
2515         1.0   1.0   89.0           Apartment
2518         1.0   1.0   40.0           Apartment
2537         1.0   2.0  125.0           Apartment
2550         1.0   2.0   47.0           Apartment
2559         1.0   1.0   25.0           Apartment
2562         1.0   1.0   80.0           Apartment
2591         1.0   4.0  120.0           Apartment
2593         1.0   1.0   40.0           Apartment
2610         1.0   1.0   50.0           Apartment
2628         1.0   1.0   60.0           Apartment
2637         1.0   1.0   30.0           Apartment
2642         1.0   1.0   70.0           Apartment
2643         1.0   1.0   48.0           Apartment
2647         1.0   1.0   60.0           Apartment
2655         1.0   2.0   40.0           Apartment
2720         1.0   2.0   80.0           Apartment
2722         1.0   2.0   45.0           Apartment
2728         1.0   1.0   50.0           Apartment
2738         1.0   1.0   40.0           Apartment
2748         1.0   2.0   70.0           Apartment
2750         1.0   2.0   95.0                Loft
2788         1.0   3.0   67.0           Apartment
2797         1.0   1.0   55.0                Loft
2810         1.0   2.0   75.0           Apartment
2817         1.0   2.0   60.0           Apartment
2819         2.0   1.0   18.0           Apartment
2830         1.0   2.0   60.0           Apartment
2835         1.0   1.0   29.0           Apartment
2847         1.0   1.0   48.0           Apartment
2868         1.0   2.0   74.0           Apartment
2887         1.0   1.0   90.0           Apartment
2888         1.0   1.0   46.0           Apartment
2900         1.0   2.0   62.0                Loft
2933         1.0   1.0   43.0           Apartment
2954         1.0   1.0   89.0           Apartment
2959         1.0   1.0   55.0           Apartment
3001         1.0   2.0   50.0           Apartment
3004         1.0   1.0   43.0           Apartment
3020         1.0   1.0   36.0           Apartment
3022         1.0   1.0   40.0           Apartment
3025         1.0   2.0   65.0           Apartment
3038         1.0   2.0   49.0           Apartment
3059         1.0   1.0   38.0           Apartment
3060         1.0   1.0   30.0           Apartment
3072         1.0   1.0   29.0           Apartment
3081         1.0   1.0   54.0           Apartment
3100         1.0   1.0   69.0           Apartment
3118         1.0   1.0   45.0           Apartment
3148         1.0   3.0   89.0           Apartment
3151         1.0   1.0   50.0           Apartment
3163         1.0   2.0   60.0           Apartment
3172         1.0   1.0   45.0           Apartment
3185         1.0   1.0   40.0           Apartment
3207         2.0   4.0  100.0           Apartment
3218         1.0   4.0   59.0           Apartment
3243         1.0   3.0   90.0           Apartment
3256         1.0   1.0   38.0           Apartment
3262         1.0   1.0   45.0               Other
3272         1.0   2.0   75.0           Apartment
3279         1.0   3.0   55.0           Apartment
3290         1.0   2.0   60.0           Apartment
3322         1.0   1.0  100.0           Apartment
3325         1.0   2.0   64.0           Apartment
3338         1.0   1.0   65.0           Apartment
3340         1.0   1.0   75.0           Apartment
3367         2.0   2.0   80.0                Loft
3383         1.0   1.0   50.0           Apartment
3394         1.0   1.0   50.0           Apartment
3443         1.0   1.0   79.0                Loft
3444         1.0   1.0   50.0         Condominium
3447         1.0   2.0   89.0           Apartment
3470         1.0   1.0   30.0           Apartment
3480         1.0   1.0   45.0           Apartment
3509         1.0   1.0   45.0           Apartment
3515         1.0   1.0   33.0           Apartment
3554         1.0   1.0   53.0           Apartment
3586         1.0   1.0   98.0           Apartment
3598         1.0   1.0   89.0           Apartment
3616         1.0   2.0   76.0           Apartment
3626         1.0   2.0   50.0           Apartment
3628         1.0   1.0   63.0           Apartment
3630         1.0   1.0   60.0           Apartment
3646         1.0   2.0   49.0           Apartment
3650         1.0   1.0   41.0           Apartment
3656         1.0   2.0   60.0               House
3658         1.0   1.0   45.0           Apartment
3673         1.0   2.0   65.0           Apartment
3678         1.0   2.0   60.0           Apartment
3692         1.0   1.0   41.0           Apartment
3696         1.0   1.0   50.0               Other
3699         1.0   2.0   80.0           Apartment
3705         1.0   1.0   34.0           Apartment
3719         1.0   2.0   45.0           Apartment
3721         1.0   2.0   55.0           Apartment
3727         1.0   1.0   55.0           Apartment
3736         1.0   4.0   69.0           Apartment
3767         1.0   1.0   40.0           Apartment
3825         1.0   1.0   50.0                Loft
3838         1.0   2.0   50.0           Apartment
3847         1.0   2.0   45.0           Apartment
3857         1.0   2.0   42.0           Apartment
3869         1.0   1.0   70.0           Apartment
3881         1.0   1.0   55.0           Apartment
3889         1.0   3.0   65.0           Apartment
3899         1.0   1.0   49.0           Apartment
3923         1.0   2.0   40.0           Apartment
3928         1.0   1.0   90.0           Apartment
3976         1.0   1.0   43.0                Loft
3985         1.0   1.0   65.0           Apartment
3990         1.0   1.0   46.0           Apartment
4007         1.0   2.0   60.0           Apartment
4012         1.0   2.0   50.0           Apartment
4024         1.0   1.0   43.0                Loft
4029         1.0   1.0   54.0           Apartment
4083         1.0   1.0   60.0           Apartment
4152         1.0   1.0   45.0           Apartment
4156         1.0   1.0   75.0           Apartment
4164         1.0   1.0   30.0           Apartment
4165         1.0   2.0   50.0           Apartment
4171         1.0   2.0   75.0           Apartment
4184         1.0   1.0   43.0           Apartment
4189         1.0   2.0   30.0           Apartment
4191         1.0   2.0   57.0           Apartment
4202         1.0   2.0   50.0           Apartment
4215         1.0   1.0   50.0           Apartment
4216         1.0   2.0   50.0           Apartment
4220         1.0   1.0   42.0                Loft
4258         1.0   1.0   45.0           Apartment
4271         1.0   2.0   43.0                Loft
4316         1.0   2.0   50.0           Apartment
4331         1.0   1.0   36.0           Apartment
4333         1.0   2.0   50.0           Apartment
4337         1.0   1.0   60.0           Apartment
4361         1.0   2.0   97.0           Apartment
4366         1.0   1.0   60.0           Apartment
4368         1.0   1.0   70.0           Apartment
4381         1.0   1.0   49.0           Apartment
4387         1.0   2.0   95.0           Apartment
4392         1.0   1.0   76.0           Apartment
4452         1.0   1.0   45.0           Apartment
4455         1.0   2.0   69.0           Apartment
4461         1.0   1.0   50.0                Loft
4465         1.0   1.0   45.0           Apartment
4501         1.0   1.0   50.0         Condominium
4532         1.0   3.0   59.0           Apartment
4536         1.0   2.0   50.0           Apartment
4543         1.0   2.0   69.0         Condominium
4549         1.0   2.0   45.0           Apartment
4555         1.0   2.0   47.0           Apartment
4561         1.0   2.0   44.0         Condominium
4568         1.0   1.0   75.0                Loft
4619         1.0   1.0   65.0           Apartment
4628         1.0   1.0   74.0           Apartment
4638         1.0   2.0   49.0           Apartment
4649         1.0   1.0   42.0           Apartment
4654         1.0   2.0   75.0           Apartment
4660         1.0   2.0   60.0               House
4668         1.0   1.0   48.0           Apartment
4706         1.0   1.0   18.0           Apartment
4712         1.0   1.0   90.0           Apartment
4716         1.0   1.0   43.0           Apartment
4733         1.0   1.0   43.0           Apartment
4736         1.0   2.0   55.0                Loft
4737         1.0   2.0   89.0           Apartment
4761         1.0   1.0   80.0           Apartment
4784         1.0   1.0   49.0           Apartment
4814         1.0   1.0   80.0           Apartment
4827         1.0   1.0   84.0           Apartment
4831         1.0   1.0   47.0              Hostel
4846         1.0   2.0   70.0           Apartment
4848         1.0   1.0   49.0           Apartment
4876         1.0   2.0   50.0               Other
4892         1.0   3.0   70.0           Apartment
4903         1.0   1.0   35.0         Condominium
4909         1.0   2.0   59.0           Apartment
4919         1.0   1.0   39.0           Apartment
4921         1.0   3.0   55.0           Apartment
4926         1.0   1.0   45.0               Other
4927         1.0   2.0   64.0           Apartment
4940         1.0   1.0   79.0           Apartment
4960         1.0   1.0   14.0           Apartment
4980         1.0   1.0   80.0                Loft
5003         1.0   2.0   79.0           Apartment
5006         1.0   1.0   80.0           Apartment
5021         1.0   1.0   41.0           Apartment
5036         1.0   3.0   60.0           Apartment
5041         1.0   1.0   90.0           Apartment
5070         1.0   1.0   47.0           Apartment
5083         1.0   1.0   55.0           Apartment
5092         1.0   1.0   70.0           Apartment
5099         1.0   1.0   58.0           Apartment
5155         1.0   2.0   50.0           Apartment
5173         1.0   1.0   70.0           Apartment
5222         1.0   1.0   48.0           Apartment
5227         1.0   2.0   50.0           Apartment
5234         1.0   1.0   55.0           Apartment
5239         1.0   1.0   65.0           Apartment
5254         1.0   1.0   89.0           Apartment
5265         1.0   1.0   45.0           Apartment
5288         1.0   1.0   52.0           Apartment
5293         1.0   1.0   50.0           Apartment
5303         1.0   2.0   70.0           Apartment
5311         1.0   1.0   29.0           Apartment
5329         1.0   2.0   55.0           Apartment
5354         1.0   3.0  100.0         Condominium
5360         1.0   1.0   60.0           Apartment
5371         1.0   2.0   80.0           Apartment
5376         1.0   2.0   50.0           Apartment
5397         1.0   2.0   55.0                Loft
5405         1.0   1.0   55.0           Apartment
5435         1.0   1.0   43.0           Apartment
5518         1.0   1.0   25.0           Apartment
5520         1.0   2.0   50.0           Apartment
5535         1.0   1.0   99.0           Apartment
5546         1.0   1.0   79.0           Apartment
5567         1.0   1.0   39.0           Apartment
5573         1.0   1.0   49.0           Apartment
5588         1.0   1.0   35.0           Apartment
5593         1.0   1.0   50.0           Apartment
5596         1.0   1.0   47.0                Loft
5604         1.0   2.0   60.0           Apartment
5641         1.0   1.0   52.0           Apartment
5673         1.0   2.0   55.0           Apartment
5679         1.0   1.0   69.0           Apartment
5691         1.0   1.0   55.0           Apartment
5694         1.0   1.0   85.0           Apartment
5700         1.0   1.0   76.0           Apartment
5710         1.0   1.0   50.0           Apartment
5719         1.0   2.0   50.0           Apartment
5722         1.0   2.0   79.0           Apartment
5765         1.0   1.0   66.0           Apartment
5771         1.0   2.0   38.0                Loft
5796         1.0   1.0   32.0           Apartment
5798         1.0   2.0   45.0           Apartment
5799         1.0   1.0   60.0           Apartment
5800         1.0   1.0   90.0           Apartment
5811         1.0   1.0   60.0           Apartment
5822         1.0   1.0   50.0           Apartment
5828         1.0   2.0   50.0     Bed & Breakfast
5855         1.0   1.0   40.0           Apartment
5866         1.0   1.0   72.0           Apartment
5888         1.0   1.0   73.0           Apartment
5895         1.0   2.0   50.0           Apartment
5897         1.0   2.0   40.0           Apartment
5901         1.0   1.0   38.0               Other
5909         1.0   1.0   60.0           Apartment
5914         1.0   1.0   50.0           Apartment
5936         1.0   1.0   74.0           Apartment
5954         1.0   1.0   30.0           Apartment
6024         1.0   1.0   28.0           Apartment
6050         1.0   1.0   50.0         Condominium
6052         1.0   1.0   54.0                Loft
6069         1.0   1.0   44.0  Serviced apartment
6070         1.5   2.0  100.0           Apartment
6077         1.0   1.0   90.0           Apartment
6084         1.0   1.0   38.0           Apartment
6121         1.0   1.0   49.0           Apartment
6122         1.0   2.0  155.0           Apartment
6124         1.0   1.0   60.0           Apartment
6126         1.0   2.0   55.0         Condominium
6146         1.0   1.0   45.0           Apartment
6147         1.0   2.0   49.0           Apartment
6154         1.0   1.0   35.0           Apartment
6157         1.0   1.0   55.0           Apartment
6161         1.0   2.0   89.0           Apartment
6169         1.0   2.0   35.0           Apartment
6198         1.0   1.0   55.0           Apartment
6256         1.0   1.0   59.0           Apartment
6257         1.0   1.0   60.0           Apartment
6264         1.0   2.0   45.0                Loft
6278         1.0   1.0   55.0           Apartment
6281         1.0   1.0   35.0           Apartment
6294         2.0   1.0   40.0           Apartment
6299         1.0   1.0   50.0           Apartment
6307         1.0   1.0   34.0           Apartment
6309         1.0   1.0   70.0                Loft
6327         1.5   1.0   48.0                Loft
6350         1.0   1.0   40.0           Apartment
6352         1.0   2.0   42.0  Serviced apartment
6353         1.0   4.0   70.0           Apartment
6358         1.0   1.0   95.0           Apartment
6373         1.0   2.0  100.0           Apartment
6382         1.0   1.0   38.0           Apartment
6383         1.0   1.0   79.0           Apartment
6434         1.0   1.0   60.0           Apartment
6445         1.0   2.0   50.0           Apartment
6470         1.0   2.0   69.0           Apartment
6501         1.0   3.0   70.0           Apartment
6559         1.0   1.0   89.0           Apartment
6565         1.0   1.0   45.0           Apartment
6567         1.0   1.0   43.0               Other
6580         1.0   1.0   65.0           Apartment
6581         1.0   1.0  139.0           Apartment
6604         1.0   2.0   33.0           Apartment
6642         1.0   1.0   75.0           Apartment
6649         1.0   2.0   76.0           Apartment
6666         1.0   2.0   75.0           Apartment
6670         1.0   4.0   50.0           Apartment
6678         1.0   1.0   40.0           Apartment
6682         1.0   3.0  100.0           Apartment
6697         1.0   1.0   55.0           Apartment
6713         1.0   1.0   39.0           Apartment
6720         1.0   2.0   85.0                Loft
6753         1.0   1.0   39.0           Apartment
6754         1.0   1.0   39.0           Apartment
6771         1.0   1.0   50.0               House
6805         1.0   1.0   35.0           Apartment
6813         1.0   1.0   33.0           Apartment
6818         1.0   2.0   60.0           Apartment
6828         1.0   3.0   60.0           Apartment
6836         1.0   1.0   47.0           Apartment
6854         1.0   2.0   47.0           Apartment
6859         1.0   2.0   40.0           Apartment
6880         1.0   1.0   60.0           Apartment
6912         1.0   1.0   68.0                Loft
6916         1.0   2.0   55.0           Apartment
6917         1.0   1.0   78.0           Apartment
6950         1.0   2.0   45.0           Apartment
6951         1.0   2.0   42.0           Apartment
6957         1.0   3.0  127.0           Apartment
6966         1.0   1.0   80.0           Apartment
6993         1.0   4.0   65.0           Apartment
7044         1.0   2.0  113.0           Apartment
7063         1.0   2.0   40.0           Apartment
7076         1.0   3.0  130.0           Apartment
7077         1.0   1.0   60.0               Other
7110         2.0   1.0   90.0                Loft
7131         1.0   1.0   50.0           Apartment
7139         1.0   2.0   50.0           Apartment
7144         1.0   2.0   59.0           Apartment
7169         1.0   1.0   50.0           Apartment
7177         1.0   1.0   60.0           Apartment
7184         1.0   1.0   39.0           Apartment
7195         1.0   2.0   45.0           Apartment
7198         1.0   1.0   25.0           Apartment
7214         1.0   1.0   50.0           Apartment
7216         1.0   2.0   49.0           Apartment
7226         1.0   2.0   70.0           Apartment
7267         1.0   2.0   45.0           Apartment
7309         1.0   1.0   40.0           Apartment
7315         1.0   1.0   54.0           Apartment
7316         1.0   1.0   75.0           Apartment
7369         1.0   2.0   50.0           Apartment
7372         1.0   1.0   49.0           Apartment
7394         1.0   1.0   72.0           Apartment
7403         1.0   1.0   49.0           Apartment
7406         1.0   1.0   58.0           Apartment
7415         1.0   1.0   59.0           Apartment
7428         1.0   1.0   38.0           Apartment
7433         1.0   1.0   45.0           Apartment
7466         1.0   1.0   23.0           Apartment
7471         1.0   1.0   49.0           Apartment
7491         1.0   1.0   36.0                Loft
7509         1.0   2.0   37.0           Apartment
7512         1.0   3.0   55.0           Apartment
7525         1.0   2.0  100.0           Apartment
7545         1.0   1.0   40.0           Apartment
7550         1.0   1.0   55.0                Loft
7555         1.0   1.0   39.0           Apartment
7585         1.0   2.0   70.0           Apartment
7614         1.0   2.0   82.0           Apartment
7624         1.0   2.0   81.0           Apartment
7629         1.0   1.0   38.0           Apartment
7687         1.0   1.0   65.0           Apartment
7701         1.0   2.0   42.0           Apartment
7720         1.0   2.0   59.0           Apartment
7777         1.0   2.0   30.0           Apartment
7785         1.0   1.0   70.0           Apartment
7794         1.0   1.0   60.0           Apartment
7806         1.0   1.0   85.0           Apartment
7823         1.0   2.0   29.0           Apartment
7847         1.0   2.0   89.0           Apartment
7890         1.0   1.0   60.0                Loft
7932         1.0   1.0   68.0           Apartment
7935         1.0   1.0   95.0           Apartment
7943         1.0   2.0   35.0           Apartment
7956         1.0   2.0   69.0                Loft
7969         1.0   1.0   30.0         Condominium
7976         1.0   1.0   44.0           Apartment
7977         1.0   2.0   60.0                Loft
8020         1.0   2.0   45.0           Apartment
8021         1.0   1.0   80.0           Apartment
8045         1.0   2.0   65.0           Apartment
8046         1.0   1.0   48.0           Apartment
8095         1.0   1.0   82.0         Condominium
8107         1.0   1.0   55.0           Apartment
8110         1.0   2.0   54.0           Apartment
8114         1.0   1.0   59.0           Apartment
8135         1.0   2.0   55.0           Apartment
8136         1.0   1.0   45.0           Apartment
8146         1.0   1.0   50.0           Apartment
8165         1.0   1.0   65.0           Apartment
8166         1.0   1.0   45.0                Loft
8167         1.0   1.0   65.0           Apartment
8187         1.0   1.0   49.0           Apartment
8199         1.0   4.0   89.0           Apartment
8204         1.0   1.0   70.0           Apartment
8221         1.0   1.0   52.0         Condominium
8226         1.0   2.0   45.0           Apartment
8238         1.0   2.0   59.0                Loft
8314         1.0   1.0   55.0           Apartment
8326         1.0   2.0   45.0           Apartment
8333         1.0   1.0   35.0           Apartment
8356         1.0   2.0   85.0           Apartment
8400         1.0   2.0   80.0           Apartment
8402         1.0   1.0   99.0                Loft
8409         1.0   1.0   32.0  Serviced apartment
8418         1.0   1.0   52.0           Apartment
8420         1.0   1.0   44.0           Apartment
8431         1.0   2.0   65.0           Apartment
8442         1.0   1.0   45.0           Apartment
8451         1.0   1.0   70.0           Apartment
8468         1.0   1.0   55.0                Loft
8482         1.0   3.0   61.0           Apartment
8505         1.0   2.0   80.0           Apartment
8516         1.0   2.0   60.0           Apartment
8525         1.0   2.0   68.0           Apartment
8553         1.0   1.0   61.0           Apartment
8573         1.0   1.0   50.0           Apartment
8592         1.0   1.0   30.0           Apartment
8600         1.0   1.0   35.0           Apartment
8614         1.0   2.0   80.0                Loft
8617         1.0   1.0   50.0         Condominium
8621         1.0   2.0   55.0           Apartment
8627         1.0   1.0   55.0                Loft
8638         1.0   1.0   65.0           Apartment
8650         1.0   1.0   43.0           Apartment
8658         1.0   2.0   40.0           Apartment
8659         1.0   1.0   59.0           Apartment
8664         1.0   1.0   43.0           Apartment
8668         1.0   1.0   45.0           Apartment
8669         1.0   2.0   50.0           Apartment
8732         1.0   3.0   50.0         Condominium
8743         1.0   1.0   35.0           Apartment
8772         1.0   1.0   50.0           Apartment
8785         1.0   2.0   55.0           Apartment
8787         1.0   1.0   95.0           Apartment
8794         1.0   1.0   45.0           Apartment
8796         1.0   1.0  109.0           Apartment
8806         1.0   1.0   38.0           Apartment
8808         1.0   2.0   45.0           Apartment
8816         1.0   1.0   45.0           Apartment
8827         1.0   1.0   69.0                Loft
8880         1.0   1.0   45.0           Apartment
8923         1.0   1.0   47.0           Apartment
8929         1.0   1.0   49.0           Apartment
8944         1.0   1.0   55.0           Apartment
8946         1.0   2.0   70.0           Apartment
8961         1.0   1.0   55.0           Apartment
8968         1.0   1.0   70.0           Apartment
8977         1.0   1.0   51.0         Condominium
9004         1.0   1.0   45.0           Apartment
9020         1.0   1.0   65.0           Apartment
9022         1.0   1.0   70.0           Apartment
9029         1.0   1.0   90.0           Apartment
9043         1.0   5.0   50.0                Loft
9077         1.0   1.0   58.0               House
9081         1.0   2.0   35.0           Apartment
9083         1.0   2.0   60.0           Apartment
9091         1.0   2.0   40.0           Apartment
9100         1.0   1.0   75.0           Apartment
9126         1.0   1.0   30.0           Apartment
9187         1.0   1.0   40.0           Apartment
9198         1.0   3.0   70.0           Apartment
9201         1.0   2.0   51.0           Apartment
9221         1.0   1.0   55.0                Loft
9227         1.0   1.0   40.0           Apartment
9236         1.0   2.0   50.0           Apartment
9244         1.0   2.0   35.0           Apartment
9245         1.0   1.0   60.0           Apartment
9249         1.0   2.0   79.0           Apartment
9250         1.0   1.0   32.0           Apartment
9256         1.0   1.0   60.0                Loft
9303         1.0   1.0   50.0           Apartment
9332         1.0   1.0   39.0           Apartment
9336         1.0   1.0   95.0           Apartment
9340         1.0   2.0   65.0           Apartment
9366         1.0   1.0   70.0           Apartment
9372         1.0   3.0   90.0           Apartment
9377         1.0   1.0   70.0         Condominium
9391         1.0   1.0   55.0           Apartment
9395         1.0   1.0   48.0           Apartment
9414         1.0   1.0   65.0           Apartment
9422         1.0   2.0   49.0           Apartment
9433         1.0   1.0   49.0           Apartment
9458         1.0   1.0   60.0           Apartment
9472         1.0   1.0   55.0           Apartment
9478         1.0   2.0   40.0           Apartment
9498         1.0   2.0   79.0           Apartment
9518         1.0   1.0   55.0           Apartment
9523         1.0   1.0   45.0           Apartment
9526         1.0   1.0   40.0           Apartment
9567         1.0   2.0   70.0           Apartment
9575         1.0   1.0   65.0                Loft
9579         1.0   1.0   35.0           Apartment
9596         1.0   1.0   89.0           Apartment
9597         1.0   1.0   54.0           Apartment
9601         1.0   2.0   64.0           Apartment
9606         1.0   2.0   39.0           Apartment
9612         1.0   2.0   80.0           Apartment
9627         1.0   2.0   50.0           Apartment
9628         1.0   1.0   30.0           Apartment
9643         1.0   1.0   52.0                Loft
9653         1.0   2.0   63.0           Apartment
9659         1.0   1.0   59.0           Apartment
9702         1.0   2.0   80.0               House
9729         1.0   1.0   50.0           Apartment
9733         1.0   2.0   45.0           Apartment
9744         1.0   1.0   70.0           Apartment
9754         1.0   3.0   89.0           Apartment
9758         1.0   1.0   90.0               House
9765         1.0   1.0   40.0           Apartment
9780         1.0   1.0   90.0           Apartment
9791         1.0   1.0   60.0           Apartment
9792         1.0   3.0  125.0           Apartment
9801         1.0   1.0   75.0                Loft
9824         1.0   2.0   65.0           Apartment
9843         1.0   1.0   97.0           Apartment
9866         1.0   1.0   50.0           Apartment
9888         1.0   1.0   39.0           Apartment
9896         1.0   1.0   69.0           Apartment
9925         1.0   1.0   43.0           Apartment
9929         1.0   3.0   32.0           Apartment
9957         1.0   1.0   48.0           Apartment
10015        1.0   1.0   80.0           Apartment
10034        1.0   1.0   40.0           Apartment
10047        1.0   1.0   37.0                Loft
10048        1.0   2.0   51.0           Apartment
10050        1.0   1.0   50.0           Apartment
10070        1.0   2.0   61.0           Apartment
10072        1.0   2.0   45.0           Apartment
10078        1.0   1.0  112.0           Apartment
10079        1.0   1.0   75.0           Apartment
10099        1.0   2.0   60.0                Loft
10104        1.0   1.0   49.0           Apartment
10114        1.0   1.0   55.0           Apartment
10135        1.0   2.0   65.0           Apartment
10149        1.0   3.0   55.0           Apartment
10152        1.0   1.0   55.0           Apartment
10153        1.0   1.0   45.0           Apartment
10164        1.0   1.0   77.0           Apartment
10170        1.0   3.0   69.0           Apartment
10172        1.0   1.0   49.0           Apartment
10178        1.0   1.0   65.0           Apartment
10208        1.0   1.0  100.0           Apartment
10210        1.0   1.0   45.0           Apartment
10221        1.0   2.0  125.0           Apartment
10231        1.0   1.0   95.0           Apartment
10248        1.0   1.0   65.0                Loft
10272        1.0   1.0   32.0  Serviced apartment
10284        1.0   2.0   70.0                Loft
10289        1.0   2.0   42.0           Apartment
10312        1.0   1.0   45.0           Apartment
10321        1.0   2.0   50.0                Loft
10322        1.0   1.0   48.0           Apartment
10327        1.0   4.0   80.0           Apartment
10332        1.0   1.0   71.0           Apartment
10372        1.0   1.0   45.0           Apartment
10378        1.0   1.0   89.0           Apartment
10407        1.0   2.0   70.0           Apartment
10408        1.0   1.0   70.0                Loft
10422        1.0   1.0   58.0           Apartment
10423        1.0   2.0   36.0           Apartment
10446        1.0   1.0   60.0           Apartment
10468        1.0   1.0   75.0           Apartment
10484        1.0   2.0   41.0           Apartment
10503        1.0   1.0   45.0           Apartment
10515        1.0   1.0  105.0           Apartment
10533        1.0   1.0   40.0           Apartment
10575        1.0   1.0   52.0           Apartment
10602        1.0   2.0   63.0           Apartment

Registros con 7 baños o más:
      Bathrooms  Beds  Price Property Type
6674        8.0  16.0   45.0        Hostel
6735        8.0  16.0   29.0     Apartment
9259        7.0   7.0   65.0        Hostel


print(f"Registros con 0 baños:\n{data_train[data_train['Bathrooms'] == 0][['Bedrooms', 'Beds', 'Price', 'Property Type']]}")
print(f"\nApartamentos con 16 camas:\n{data_train[(data_train['Beds'] == 16) & (data_train['Property Type'] == 'Apartment')][['Price', 'Bedrooms', 'Bathrooms', 'Property Type']]}")

Registros con 0 baños:
       Bedrooms  Beds  Price    Property Type
30          1.0   1.0   75.0        Apartment
71          1.0   1.0   24.0  Bed & Breakfast
773         1.0   2.0   22.0        Apartment
1138        1.0   2.0   50.0           Hostel
1254        1.0   1.0   33.0  Bed & Breakfast
1592        1.0   1.0   20.0        Apartment
1675        1.0   2.0   24.0        Apartment
1699        1.0   8.0   21.0  Bed & Breakfast
1751        1.0   1.0   30.0        Apartment
1752        1.0   1.0   30.0        Apartment
1899        1.0   1.0   30.0        Apartment
1912        1.0   1.0  149.0             Dorm
2064        1.0   1.0   29.0        Apartment
2322        1.0   1.0   29.0            House
2405        1.0   1.0   26.0        Apartment
2914        1.0   1.0   29.0            House
3280        1.0   1.0   30.0             Dorm
3458        1.0   2.0   39.0            House
3513        1.0   3.0   53.0       Guesthouse
3538        1.0   1.0   27.0      Condominium
3874        1.0   1.0   29.0            House
4112        1.0   1.0   20.0        Apartment
4124        1.0   2.0   18.0  Bed & Breakfast
4507        1.0   2.0   39.0            House
4770        1.0   1.0   31.0        Apartment
4925        1.0   1.0    9.0            Other
5098        1.0   1.0   25.0        Apartment
5905        1.0  10.0   20.0  Bed & Breakfast
6006        1.0   1.0   35.0        Apartment
6729        1.0   3.0   18.0             Dorm
6918        1.0   2.0   39.0            House
7053        1.0   1.0   49.0        Apartment
7246        1.0   1.0   20.0        Apartment
7706        1.0   1.0   35.0        Apartment
7916       10.0   2.0   39.0            House
8060        1.0   2.0   39.0            House
8273        1.0   1.0   29.0        Apartment
8406        1.0   2.0   39.0            House
8629        1.0   1.0   43.0        Apartment
8677        1.0   1.0   20.0  Bed & Breakfast
8767        1.0   1.0   30.0  Bed & Breakfast
8780        1.0   2.0   25.0        Apartment
8797        1.0   1.0   35.0        Apartment
8851        1.0   2.0   35.0  Bed & Breakfast
8903        1.0   1.0   49.0        Apartment
8936        1.0   1.0   35.0        Apartment
9401        1.0   1.0   35.0        Apartment
9473        1.0   1.0   20.0  Bed & Breakfast
9625        1.0   1.0   35.0        Apartment
9812        1.0   1.0   50.0        Apartment
9870        1.0   4.0   24.0  Bed & Breakfast
10202       1.0   1.0   35.0        Apartment
10376       1.0   1.0   30.0        Apartment

Apartamentos con 16 camas:
      Price  Bedrooms  Bathrooms Property Type
664   200.0       6.0        2.0     Apartment
2437  400.0       6.0        6.0     Apartment
3859  180.0      10.0        6.0     Apartment
5502   80.0       4.0        2.0     Apartment
5557  850.0      10.0        6.5     Apartment
5705  399.0       8.0        4.5     Apartment
6539  200.0       5.0        2.0     Apartment
6735   29.0       1.0        8.0     Apartment
7303  550.0       7.0        3.0     Apartment
8286  338.0       5.0        2.0     Apartment


sns.set_theme(style="white")
sns.relplot(x='Square Feet', y='Price', data=data_train, hue='Room Type', alpha=0.8)
plt.title('Relación entre Pies Cuadrados y Precio')
plt.xlabel('Pies Cuadrados', fontsize=10)
plt.ylabel('Precio', fontsize=10)
plt.show()


corr_matrix = data_train.select_dtypes(include=[np.number]).corr()
attributes = ['Price','Accommodates','Bathrooms','Bedrooms','Beds']
plot_scatter_matrix(data_train, attributes)


# Filtro para propiedades con más de 2500 SquareFeet
properties_above_2500sqft = data_train[data_train['Square Feet'] > 2500]
print("Propiedades con más de 2500 SquareFeet:")
print(properties_above_2500sqft[['Square Feet', 'Price', 'Room Type', 'Bathrooms', 'Bedrooms', 'Beds']])

# Filtro para apartamentos con 0 SquareFeet
apartments_with_0sqft = data_train[data_train['Square Feet'] == 0]
print("\nApartamentos con 0 SquareFeet:")
print(apartments_with_0sqft[['Square Feet', 'Price', 'Bathrooms', 'Bedrooms', 'Beds']].describe())

Propiedades con más de 2500 SquareFeet:
      Square Feet  Price     Room Type  Bathrooms  Bedrooms  Beds
1495       2691.0   35.0  Private room        1.0       1.0   1.0
7346       2691.0   25.0  Private room        2.5       1.0   3.0
8580       2691.0   20.0  Private room        2.0       1.0   7.0

Apartamentos con 0 SquareFeet:
       Square Feet       Price   Bathrooms    Bedrooms        Beds
count        169.0  169.000000  165.000000  169.000000  169.000000
mean           0.0   65.147929    1.230303    1.260355    2.272189
std            0.0   39.809315    0.547992    0.734135    1.821628
min            0.0   15.000000    0.000000    0.000000    1.000000
25%            0.0   37.000000    1.000000    1.000000    1.000000
50%            0.0   60.000000    1.000000    1.000000    2.000000
75%            0.0   80.000000    1.000000    1.000000    3.000000
max            0.0  250.000000    4.000000    4.000000   16.000000


correlation_matrix = data_train[['Accommodates','Bathrooms','Bedrooms','Beds','Square Feet','Price']].corr()
plt.figure(figsize=(5, 4))
sns.heatmap(correlation_matrix, annot=True, fmt=".2f", cmap='coolwarm', cbar=True)
plt.show()


columns_to_include = ['Price', 'Weekly Price', 'Monthly Price', 'Security Deposit',
                      'Cleaning Fee', 'Guests Included', 'Extra People']
plot_histograms(data_train, columns_to_include[:3], bins=15, figsize=(20, 4))
plot_histograms(data_train, columns_to_include[3:], bins=15, figsize=(20, 4))


sns.set_style("whitegrid")
plt.figure(figsize=(12, 1.4))
sns.boxplot(x=data_train['Price'], color='cornflowerblue')
plt.title('Boxplot de Precios por Noche', fontsize='11')
plt.xlabel('Precio', fontsize='10')
sns.despine(trim=True)
plt.show()


sns.set_style("whitegrid")
plt.figure(figsize=(12, 1.4))
sns.boxplot(x=data_train['Extra People'], color='cornflowerblue')
plt.title('Boxplot de Coste Adicional por Huésped Extra', fontsize='11')
plt.xlabel('Precio', fontsize='10')
sns.despine(trim=True)
plt.show()


data_train[data_train['Extra People'] > 100][['Extra People', 'Property Type', 'Price',
                                              'Bedrooms', 'Bathrooms', 'Beds', 'Neighbourhood Cleansed']]


attributes = ['Price', 'Weekly Price', 'Monthly Price', 'Security Deposit',
                'Cleaning Fee', 'Guests Included', 'Extra People']
plot_scatter_matrix(data_train, attributes)


correlation_matrix = data_train[['Weekly Price','Monthly Price','Security Deposit','Guests Included',
                         'Cleaning Fee','Extra People','Bedrooms','Bathrooms','Beds','Price']].corr()
plt.figure(figsize=(8, 6))
sns.heatmap(correlation_matrix, annot=True, fmt=".2f", cmap='coolwarm', cbar=True)
plt.show()


columns_to_include = ['Minimum Nights', 'Maximum Nights', 'Availability 30',
                      'Availability 60', 'Availability 90', 'Availability 365']
plot_histograms(data_train, columns_to_include[:3], bins=15, figsize=(20, 4))
plot_histograms(data_train, columns_to_include[3:], bins=15, figsize=(20, 4))


sns.set_style("whitegrid")
plt.figure(figsize=(12, 1.4))
sns.boxplot(x=data_train['Minimum Nights'], color='cornflowerblue')
plt.title('Distribución de Noches Mínimas', fontsize='11')
plt.xlabel('Noches', fontsize='10')
sns.despine(trim=True)
plt.show()

plt.figure(figsize=(12, 1.4))
sns.boxplot(x=data_train['Maximum Nights'], color='cornflowerblue')
plt.title('Distribución de Noches Máximas', fontsize='11')
plt.xlabel('Noches', fontsize='10')
sns.despine(trim=True)
plt.show()


attributes = ['Availability 30', 'Availability 60', 'Availability 90', 'Availability 365', 'Price']
plot_scatter_matrix(data_train, attributes)


correlation_matrix = data_train[['Minimum Nights','Maximum Nights', 'Availability 30',
                                 'Availability 60','Availability 90','Availability 365','Price']].corr()
plt.figure(figsize=(6, 4))
sns.heatmap(correlation_matrix, annot=True, fmt=".2f", cmap='coolwarm', cbar=True)
plt.show()


columns_to_include = ['Number of Reviews','Review Scores Rating','Review Scores Accuracy',
                      'Review Scores Cleanliness','Review Scores Checkin','Review Scores Communication',
                      'Review Scores Location','Review Scores Value','Reviews per Month',
                      'Calculated host listings count']
plot_histograms(data_train, columns_to_include[:5], bins=15, figsize=(20, 4))
plot_histograms(data_train, columns_to_include[5:], bins=15, figsize=(20, 4))


attributes = ['Number of Reviews','Review Scores Rating','Review Scores Accuracy','Review Scores Cleanliness',
              'Review Scores Checkin','Review Scores Communication','Review Scores Location',
              'Review Scores Value','Reviews per Month','Calculated host listings count']
plot_scatter_matrix(data_train, attributes, figsize=(20, 12))


# Seleccionamos las columnas de interés para la correlación
columns_of_interest = ['Number of Reviews','Review Scores Rating','Review Scores Accuracy',
                       'Review Scores Cleanliness','Review Scores Checkin','Review Scores Communication',
                       'Review Scores Location','Review Scores Value','Reviews per Month',
                       'Calculated host listings count','Price']

correlation_matrix = data_train[columns_of_interest].corr()
plt.figure(figsize=(8, 6))
sns.heatmap(correlation_matrix, annot=True, fmt=".2f", cmap='coolwarm', cbar=True)
plt.show()


sns.set_style("whitegrid")

data_train_no_outliers = data_train[~((data_train['Bedrooms'] > 6) & (data_train['Beds'] < 4))]
data_train_no_outliers2 = data_train[data_train['Bathrooms'] <= 7]
data_train_no_outliers3 = data_train[data_train['Bedrooms'] <= 8]

fig, axs = plt.subplots(nrows=1, ncols=3, figsize=(18, 6))

# Primer gráfico: Dormitorios vs Precio
axs[0].scatter(data_train_no_outliers['Bedrooms'], data_train_no_outliers['Price'], color='royalblue')
axs[0].set_xlabel('Dormitorios')
axs[0].set_ylabel('Precio')
axs[0].set_title('Alojamientos con menos de 6 dormitorios y más de 4 camas')

# Tercer gráfico: Dormitorios vs Precio (sin outliers2)
axs[1].scatter(data_train_no_outliers2['Bedrooms'], data_train_no_outliers2['Price'], color='crimson')
axs[1].set_xlabel('Dormitorios')
axs[1].set_ylabel('Precio')
axs[1].set_title('Alojamientos con menos de 7 baños')

# Quinto gráfico: Dormitorios vs Precio (sin outliers2)
axs[2].scatter(data_train_no_outliers3['Bedrooms'], data_train_no_outliers3['Price'], color='lightseagreen')
axs[2].set_xlabel('Dormitorios')
axs[2].set_ylabel('Precio')
axs[2].set_title('Alojamientos con menos de 8 dormitorio')

plt.tight_layout()
sns.despine(top=True, right=True, left=False, bottom=False)

fig, axs = plt.subplots(nrows=1, ncols=3, figsize=(18, 6))

# Segundo gráfico: Baños vs Precio
axs[0].scatter(data_train_no_outliers['Bathrooms'], data_train_no_outliers['Price'], color='royalblue')
axs[0].set_xlabel('Baños')
axs[0].set_ylabel('Precio')
axs[0].set_title('Alojamientos con menos de 6 dormitorios y más de 4 camas')

# Cuarto gráfico: Baños vs Precio (sin outliers2)
axs[1].scatter(data_train_no_outliers2['Bathrooms'], data_train_no_outliers2['Price'], color='crimson')
axs[1].set_xlabel('Baños')
axs[1].set_ylabel('Precio')
axs[1].set_title('Alojamientos con menos de 7 baños')

# Sexto gráfico: Baños vs Precio (sin outliers2)
axs[2].scatter(data_train_no_outliers3['Bathrooms'], data_train_no_outliers3['Price'], color='lightseagreen')
axs[2].set_xlabel('Baños')
axs[2].set_ylabel('Precio')
axs[2].set_title('Alojamientos con menos de 8 dormitorios')

plt.tight_layout()
sns.despine(top=True, right=True, left=False, bottom=False)
plt.show()


print(f'Original: {data_train.shape[0]} // Modificado: {data_train_no_outliers.shape[0]}\nDiferencia: {data_train.shape[0] - data_train_no_outliers.shape[0]}')
print(f'Variación: {((data_train.shape[0] - data_train_no_outliers.shape[0])/data_train.shape[0])*100:2f}%')
print(f'\nOriginal: {data_train.shape[0]} // Modificado: {data_train_no_outliers2.shape[0]}\nDiferencia: {data_train.shape[0] - data_train_no_outliers2.shape[0]}')
print(f'Variación: {((data_train.shape[0] - data_train_no_outliers2.shape[0])/data_train.shape[0])*100:2f}%')
print(f'\nOriginal: {data_train.shape[0]} // Modificado: {data_train_no_outliers3.shape[0]}\nDiferencia: {data_train.shape[0] - data_train_no_outliers3.shape[0]}')
print(f'Variación: {((data_train.shape[0] - data_train_no_outliers3.shape[0])/data_train.shape[0])*100:2f}%')

Original: 10609 // Modificado: 10607
Diferencia: 2
Variación: 0.018852%

Original: 10609 // Modificado: 10569
Diferencia: 40
Variación: 0.377038%

Original: 10609 // Modificado: 10590
Diferencia: 19
Variación: 0.179093%


#data_train.select_dtypes(include=[np.number]).corr()


corr_matrix = data_train.select_dtypes(include=[np.number]).corr()

# Filtramos para mostrar solo las correlaciones de 'Price' superiores a 0.4 o inferiores a -0.4
strong_correlations = corr_matrix["Price"][(corr_matrix["Price"] > 0.4) | (corr_matrix["Price"] < -0.4)]
print(strong_correlations.sort_values(ascending=False))

Price            1.000000
Monthly Price    0.838666
Weekly Price     0.830605
Cleaning Fee     0.656235
Accommodates     0.572179
Bedrooms         0.514831
Beds             0.471162
Name: Price, dtype: float64


data = data_train.select_dtypes(include=[np.number])
corr = np.abs(data.drop(['Price'], axis=1).corr())

mask = np.zeros_like(corr, dtype = bool)
mask[np.triu_indices_from(mask)] = True

f, ax = plt.subplots(figsize=(12, 10))

sns.heatmap(corr, mask=mask,vmin = 0.0, vmax=1.0, center=0.5,
            linewidths=.1, cmap="YlGnBu", cbar_kws={"shrink": .8})

plt.show()


data_train['LatLongInteraction']  = data_train['Latitude'] * data_train['Longitude']

# Si el número de dormitorios es mayor que cero, realiza la división, de lo contrario devuelve cero.
data_train['BedsPerRoom'] = data_train.apply(lambda row: row['Beds'] / row['Bedrooms'] if row['Bedrooms'] > 0 else 0, axis=1)
data_train['BathsPerRoom'] = data_train.apply(lambda row: row['Bathrooms'] / row['Bedrooms'] if row['Bedrooms'] > 0 else 0, axis=1)

data_train['PricePerBed'] = data_train['Price'] / data_train['Beds']
data_train['BedBathRooms'] = data_train['Bedrooms'] * data_train['Bathrooms']

print(data_train[['LatLongInteraction','BedsPerRoom','BathsPerRoom','PricePerBed','BedBathRooms']].describe())

       LatLongInteraction   BedsPerRoom  BathsPerRoom   PricePerBed  \
count        10609.000000  10583.000000  10571.000000  10568.000000   
mean          -149.441245      1.356939      0.952190     37.987937   
std              0.944412      0.932363      0.577699     28.433538   
min           -156.730652      0.000000      0.000000      1.100000   
25%           -149.860933      1.000000      0.666667     22.312500   
50%           -149.614689      1.000000      1.000000     30.000000   
75%           -149.284273      2.000000      1.000000     46.000000   
max           -142.562833     16.000000      8.000000    650.000000   

       BedBathRooms  
count  10557.000000  
mean       1.842853  
std        2.583767  
min        0.000000  
25%        1.000000  
50%        1.000000  
75%        2.000000  
max       65.000000


# Creamos una columna que refleje la duración de la estancia
def classify_stay(min_nights, max_nights):
    if min_nights == 1 and max_nights <= 7:
        return 1  # Estancias cortas
    elif 7 < min_nights <= 30 or (min_nights <= 7 and 7 < max_nights <= 30):
        return 2  # Estancias medias
    elif 30 < min_nights <= 365 or (min_nights <= 30 and 30 < max_nights <= 365):
        return 3  # Estancias largas
    elif min_nights > 365 or max_nights > 365:
        return 4  # Estancias muy largas
    else:
        return 0  # Casos atípicos o no clasificables

data_train['Stay Duration'] = data_train.apply(lambda row: classify_stay(row['Minimum Nights'], row['Maximum Nights']), axis=1)
print(data_train[['Stay Duration', 'Minimum Nights', 'Maximum Nights']].describe())
print(data_train[['Stay Duration']].value_counts())
#data_train[['Stay Duration', 'Minimum Nights', 'Maximum Nights']].head()

       Stay Duration  Minimum Nights  Maximum Nights
count   10609.000000    10609.000000    10609.000000
mean        3.435197        3.014045      980.265906
std         0.982103       12.840494     9908.895741
min         0.000000        1.000000        1.000000
25%         3.000000        1.000000      365.000000
50%         4.000000        2.000000     1125.000000
75%         4.000000        3.000000     1125.000000
max         4.000000     1125.000000  1000000.000000
Stay Duration
4                7421
2                1523
3                1147
1                 273
0                 245
Name: count, dtype: int64


# Filtramos posibles outliers
def filter_data(data):
    filtered_data = data[~((data['Bedrooms'] > 6) & (data['Beds'] < 4))]
    filtered_data = filtered_data[filtered_data['Bedrooms'] <= 8]
    filtered_data = filtered_data[(filtered_data['Bathrooms'] <= 6) & (filtered_data['Bathrooms'] > 0)]
    
    return filtered_data

data_train = filter_data(data_train)


columns_to_drop = [
    'ID', 'Listing Url', 'Scrape ID', 'Last Scraped', 'Calendar last Scraped',
    'License', 'Jurisdiction Names', 'Host URL', 'Host About', 'Name', 'Summary',
    'Space', 'Description', 'Notes', 'Neighborhood Overview', 'Transit', 'Access',
    'Interaction', 'House Rules', 'Thumbnail Url', 'Medium Url', 'Picture Url',
    'XL Picture Url', 'Host Thumbnail Url', 'Host Picture Url', 'Host Acceptance Rate',
    'Has Availability', 'Host Total Listings Count', 'Geolocation', 'Neighbourhood',
    'Host ID', 'Host Name', 'Host Location', 'Host Neighbourhood', 'Host About',
    'Host Total Listings Count', 'Experiences Offered', 'Street', 'City', 'State',
    'Country Code', 'Country', 'Market', 'Smart Location', 'Latitude', 'Longitude', 'Zipcode',
    'Host Response Time', 'Square Feet', 'Weekly Price', 'Monthly Price', 'Security Deposit',
    'Availability 30', 'Availability 60', 'Availability 90', 'Availability 365', 'Minimum Nights',
    'Maximum Nights', 'Calendar Updated', 'Geolocation', 'Number of Reviews', 
    'Review Scores Accuracy', 'Review Scores Cleanliness', 'Review Scores Rating',
    'Review Scores Checkin', 'Review Scores Communication', 'Review Scores Location',
    'Review Scores Value', 'Reviews per Month', 'Calculated host listings count',
    'Host Response Rate', 'First Review', 'Last Review'
]
data_train = data_train.drop(columns_to_drop, axis=1)


data_train.info()

<class 'pandas.core.frame.DataFrame'>
Index: 10497 entries, 0 to 10608
Data columns (total 25 columns):
 #   Column                        Non-Null Count  Dtype  
---  ------                        --------------  -----  
 0   Host Since                    10495 non-null  object 
 1   Host Listings Count           10495 non-null  float64
 2   Host Verifications            10494 non-null  object 
 3   Neighbourhood Cleansed        10497 non-null  object 
 4   Neighbourhood Group Cleansed  10497 non-null  object 
 5   Property Type                 10497 non-null  object 
 6   Room Type                     10497 non-null  object 
 7   Accommodates                  10497 non-null  int64  
 8   Bathrooms                     10497 non-null  float64
 9   Bedrooms                      10497 non-null  float64
 10  Beds                          10490 non-null  float64
 11  Bed Type                      10497 non-null  object 
 12  Amenities                     10434 non-null  object 
 13  Price                         10489 non-null  float64
 14  Cleaning Fee                  6227 non-null   float64
 15  Guests Included               10497 non-null  int64  
 16  Extra People                  10497 non-null  int64  
 17  Cancellation Policy           10497 non-null  object 
 18  Features                      10497 non-null  object 
 19  LatLongInteraction            10497 non-null  float64
 20  BedsPerRoom                   10490 non-null  float64
 21  BathsPerRoom                  10497 non-null  float64
 22  PricePerBed                   10482 non-null  float64
 23  BedBathRooms                  10497 non-null  float64
 24  Stay Duration                 10497 non-null  int64  
dtypes: float64(11), int64(4), object(10)
memory usage: 2.1+ MB


data_train['Cancellation Policy'].value_counts()

Cancellation Policy
strict             3980
flexible           3385
moderate           3126
super_strict_60       4
super_strict_30       2
Name: count, dtype: int64


# Calculamos la antigüedad en días desde la fecha 'Host Since' hasta la fecha actual
data_train['Host Since'] = pd.to_datetime(data_train['Host Since'])
data_train['Host Since'] = (pd.Timestamp.now().normalize() - data_train['Host Since']).dt.days

# Indicará la cantidad total de verificaciones
data_train['Host Verifications'] = data_train['Host Verifications'].apply(lambda x: len(x.split(',')) if pd.notna(x) else 0)

# Creamos una nueva columna que sea 1 si 'Bed Type' es 'Real Bed' y 0 en caso contrario
data_train['Bed Type'] = (data_train['Bed Type'] == 'Real Bed').astype(int)

# Número total de comodidades
data_train['Amenities'] = data_train['Amenities'].dropna().str.split(',').apply(len)

# Contamos el número de Features por registro y creamos una nueva columna con esta información
data_train['Features'] = data_train['Features'].dropna().str.split(',').apply(len)


data_train['Property Type'].value_counts()

Property Type
Apartment             8679
House                  756
Condominium            279
Bed & Breakfast        259
Loft                   223
Other                  174
Guesthouse              29
Dorm                    29
Chalet                  21
Serviced apartment      12
Hostel                   8
Townhouse                8
Villa                    4
Boutique hotel           4
Casa particular          3
Guest suite              3
Earth House              3
Camper/RV                2
Tent                     1
Name: count, dtype: int64


# Función para agrupar las categorías de 'Property Type'
def group_property_type(dataframe):
    categories_to_keep = ['Apartment','House','Condominium','Bed & Breakfast','Loft']
    return dataframe['Property Type'].apply(lambda x: x if x in categories_to_keep else 'Others')

data_train['Property Type'] = group_property_type(data_train)
data_train['Property Type'].value_counts()

Property Type
Apartment          8679
House               756
Others              301
Condominium         279
Bed & Breakfast     259
Loft                223
Name: count, dtype: int64


categorical = ['Neighbourhood Cleansed', 'Neighbourhood Group Cleansed', 'Property Type', 'Room Type']
mean_map = {}

for c in categorical:
    # Calcula el promedio de precio para cada categoría
    mean = data_train.groupby(c)['Price'].mean()
    data_train[c] = data_train[c].map(mean)    
    mean_map[c] = mean


# Unir las categorías 'super_strict_60' y 'super_strict_30'
data_train['Cancellation Policy'] = data_train['Cancellation Policy'].replace(['super_strict_60', 'super_strict_30'], 'super_strict')
print(data_train['Cancellation Policy'].value_counts())

Cancellation Policy
strict          3980
flexible        3385
moderate        3126
super_strict       6
Name: count, dtype: int64


from sklearn.preprocessing import OrdinalEncoder

categories = [['flexible', 'moderate', 'strict', 'super_strict']]
cancel_cat = data_train[['Cancellation Policy']]

ordinal_encoder = OrdinalEncoder(categories=categories)
encoded_data = ordinal_encoder.fit_transform(cancel_cat)
print(encoded_data)

# Para convertir de vuelta a las etiquetas originales si fuera necesario
# decoded_data = encoder.inverse_transform(encoded_data)
# print(encoded_data)

[[1.]
 [1.]
 [1.]
 ...
 [1.]
 [1.]
 [3.]]


data_train['Cancellation Policy'] = encoded_data
print(data_train['Cancellation Policy'].dtype)

float64


# Verificamos que todas las categorías son numéricas
data_train.info()

<class 'pandas.core.frame.DataFrame'>
Index: 10497 entries, 0 to 10608
Data columns (total 25 columns):
 #   Column                        Non-Null Count  Dtype  
---  ------                        --------------  -----  
 0   Host Since                    10495 non-null  float64
 1   Host Listings Count           10495 non-null  float64
 2   Host Verifications            10497 non-null  int64  
 3   Neighbourhood Cleansed        10497 non-null  float64
 4   Neighbourhood Group Cleansed  10497 non-null  float64
 5   Property Type                 10497 non-null  float64
 6   Room Type                     10497 non-null  float64
 7   Accommodates                  10497 non-null  int64  
 8   Bathrooms                     10497 non-null  float64
 9   Bedrooms                      10497 non-null  float64
 10  Beds                          10490 non-null  float64
 11  Bed Type                      10497 non-null  int64  
 12  Amenities                     10434 non-null  float64
 13  Price                         10489 non-null  float64
 14  Cleaning Fee                  6227 non-null   float64
 15  Guests Included               10497 non-null  int64  
 16  Extra People                  10497 non-null  int64  
 17  Cancellation Policy           10497 non-null  float64
 18  Features                      10497 non-null  int64  
 19  LatLongInteraction            10497 non-null  float64
 20  BedsPerRoom                   10490 non-null  float64
 21  BathsPerRoom                  10497 non-null  float64
 22  PricePerBed                   10482 non-null  float64
 23  BedBathRooms                  10497 non-null  float64
 24  Stay Duration                 10497 non-null  int64  
dtypes: float64(18), int64(7)
memory usage: 2.1 MB


# Para imputar los datos faltantes
# La instancia imputer calcula la mediana de cada atributo y almacena el resultado en su variable de instancia statistics_
from sklearn.impute import KNNImputer

imputer = KNNImputer()

columns_to_impute = ['Host Since','Host Listings Count','Beds','Amenities',
                     'Cleaning Fee','BedsPerRoom','PricePerBed', 'Price']

# Transformamos los datos de entrenamiento sustituyendo valores que faltan por las medianas aprendidas
X_imputed = imputer.fit_transform(data_train[columns_to_impute])


# Convertimos el resultado nuevamente a un DataFrame para mantener la estructura original
data_train_imputed = pd.DataFrame(X_imputed, columns=columns_to_impute,index=data_train.index)

# Actualizamos las columnas originales en data_train con los valores imputados
data_train.update(data_train_imputed)

# Verificamos la imputación
print(data_train[columns_to_impute].isnull().sum())

Host Since             0
Host Listings Count    0
Beds                   0
Amenities              0
Cleaning Fee           0
BedsPerRoom            0
PricePerBed            0
Price                  0
dtype: int64


# Eliminamos más columnas del modelo (después de Lasso)
columns_to_drop_2 = ['Host Verifications', 'Stay Duration']
data_train = data_train.drop(columns_to_drop_2, axis=1)


# Eliminamos más columnas del modelo (tras el 2º análisis)
columns_to_drop_3 = ['Features','Bed Type','Cancellation Policy','Extra People','Neighbourhood Group Cleansed','Property Type']
data_train = data_train.drop(columns_to_drop_3, axis=1)


# Verificamos que no hay datos faltantes
data_train.info()

<class 'pandas.core.frame.DataFrame'>
Index: 10497 entries, 0 to 10608
Data columns (total 17 columns):
 #   Column                  Non-Null Count  Dtype  
---  ------                  --------------  -----  
 0   Host Since              10497 non-null  float64
 1   Host Listings Count     10497 non-null  float64
 2   Neighbourhood Cleansed  10497 non-null  float64
 3   Room Type               10497 non-null  float64
 4   Accommodates            10497 non-null  int64  
 5   Bathrooms               10497 non-null  float64
 6   Bedrooms                10497 non-null  float64
 7   Beds                    10497 non-null  float64
 8   Amenities               10497 non-null  float64
 9   Price                   10497 non-null  float64
 10  Cleaning Fee            10497 non-null  float64
 11  Guests Included         10497 non-null  int64  
 12  LatLongInteraction      10497 non-null  float64
 13  BedsPerRoom             10497 non-null  float64
 14  BathsPerRoom            10497 non-null  float64
 15  PricePerBed             10497 non-null  float64
 16  BedBathRooms            10497 non-null  float64
dtypes: float64(15), int64(2)
memory usage: 1.4 MB


# Analizar correlación con los cambios
data = data_train.select_dtypes(include=[np.number])
corr = np.abs(data.drop(['Price'], axis=1).corr())

mask = np.zeros_like(corr, dtype = bool)
mask[np.triu_indices_from(mask)] = True

f, ax = plt.subplots(figsize=(12, 10))

sns.heatmap(corr, mask=mask,vmin = 0.0, vmax=1.0, center=0.5,
            linewidths=.1, cmap="YlGnBu", cbar_kws={"shrink": .8})

plt.show()


corr_matrix = data_train.select_dtypes(include=[np.number]).corr()
print(corr_matrix["Price"].sort_values(ascending=False))

Price                     1.000000
Cleaning Fee              0.689744
Accommodates              0.572874
BedBathRooms              0.567828
PricePerBed               0.560153
Bedrooms                  0.519410
Beds                      0.474187
Room Type                 0.469757
Guests Included           0.374546
Neighbourhood Cleansed    0.354200
Bathrooms                 0.347137
Amenities                 0.213631
Host Listings Count       0.191909
BedsPerRoom               0.087661
Host Since                0.080965
LatLongInteraction       -0.044289
BathsPerRoom             -0.162766
Name: Price, dtype: float64


pd.reset_option('display.max_rows')
pd.reset_option('display.max_columns')


data_train.info()

<class 'pandas.core.frame.DataFrame'>
Index: 10497 entries, 0 to 10608
Data columns (total 17 columns):
 #   Column                  Non-Null Count  Dtype  
---  ------                  --------------  -----  
 0   Host Since              10497 non-null  float64
 1   Host Listings Count     10497 non-null  float64
 2   Neighbourhood Cleansed  10497 non-null  float64
 3   Room Type               10497 non-null  float64
 4   Accommodates            10497 non-null  int64  
 5   Bathrooms               10497 non-null  float64
 6   Bedrooms                10497 non-null  float64
 7   Beds                    10497 non-null  float64
 8   Amenities               10497 non-null  float64
 9   Price                   10497 non-null  float64
 10  Cleaning Fee            10497 non-null  float64
 11  Guests Included         10497 non-null  int64  
 12  LatLongInteraction      10497 non-null  float64
 13  BedsPerRoom             10497 non-null  float64
 14  BathsPerRoom            10497 non-null  float64
 15  PricePerBed             10497 non-null  float64
 16  BedBathRooms            10497 non-null  float64
dtypes: float64(15), int64(2)
memory usage: 1.4 MB


# Ver el índice de la columna 'Price'
price_index = data_train.columns.get_loc('Price')
price_index

9


from sklearn import preprocessing

data = data_train.values

y_train = data[:, price_index] # Extraemos la columna 'Price' usando su índice numérico
X_train = np.delete(data, price_index, axis=1)  # Eliminamos price_index de la matriz

feature_names = np.delete(data_train.columns.values, price_index)

# Escalamos (con los datos de train)
scaler = preprocessing.StandardScaler().fit(X_train)
XtrainScaled = scaler.transform(X_train)


feature_names

array(['Host Since', 'Host Listings Count', 'Neighbourhood Cleansed',
       'Room Type', 'Accommodates', 'Bathrooms', 'Bedrooms', 'Beds',
       'Amenities', 'Cleaning Fee', 'Guests Included',
       'LatLongInteraction', 'BedsPerRoom', 'BathsPerRoom', 'PricePerBed',
       'BedBathRooms'], dtype=object)


data_test = pd.read_csv('./test.csv', sep=';', decimal='.')


# Añadir nuevas características
data_test['LatLongInteraction']  = data_test['Latitude'] * data_test['Longitude']
data_test['BedsPerRoom'] = data_test.apply(lambda row: row['Beds'] / row['Bedrooms'] if row['Bedrooms'] > 0 else 0, axis=1)
data_test['BathsPerRoom'] = data_test.apply(lambda row: row['Bathrooms'] / row['Bedrooms'] if row['Bedrooms'] > 0 else 0, axis=1)
data_test['PricePerBed'] = data_test['Price'] / data_test['Beds']
data_test['BedBathRooms'] = data_test['Bedrooms'] * data_test['Bathrooms']
data_test['Stay Duration'] = data_test.apply(lambda row: classify_stay(row['Minimum Nights'], row['Maximum Nights']), axis=1)

# Filtramos outliers
data_test = filter_data(data_test) 

# Eliminamos columnas
columns_to_drop = [
    'ID', 'Listing Url', 'Scrape ID', 'Last Scraped', 'Calendar last Scraped',
    'License', 'Jurisdiction Names', 'Host URL', 'Host About', 'Name', 'Summary',
    'Space', 'Description', 'Notes', 'Neighborhood Overview', 'Transit', 'Access',
    'Interaction', 'House Rules', 'Thumbnail Url', 'Medium Url', 'Picture Url',
    'XL Picture Url', 'Host Thumbnail Url', 'Host Picture Url', 'Host Acceptance Rate',
    'Has Availability', 'Host Total Listings Count', 'Geolocation', 'Neighbourhood',
    'Host ID', 'Host Name', 'Host Location', 'Host Neighbourhood', 'Host About',
    'Host Total Listings Count', 'Experiences Offered', 'Street', 'City', 'State',
    'Country Code', 'Country', 'Market', 'Smart Location', 'Latitude', 'Longitude', 'Zipcode',
    'Host Response Time', 'Square Feet', 'Weekly Price', 'Monthly Price', 'Security Deposit',
    'Availability 30', 'Availability 60', 'Availability 90', 'Availability 365', 'Minimum Nights',
    'Maximum Nights', 'Calendar Updated', 'Geolocation', 'Number of Reviews', 
    'Review Scores Accuracy', 'Review Scores Cleanliness', 'Review Scores Rating',
    'Review Scores Checkin', 'Review Scores Communication', 'Review Scores Location',
    'Review Scores Value', 'Reviews per Month', 'Calculated host listings count',
    'Host Response Rate', 'First Review', 'Last Review'
]
data_test = data_test.drop(columns_to_drop, axis=1)

# Codificación de variables
data_test['Host Since'] = pd.to_datetime(data_test['Host Since'])
data_test['Host Since'] = (pd.Timestamp.now().normalize() - data_test['Host Since']).dt.days
data_test['Host Verifications'] = data_test['Host Verifications'].apply(lambda x: len(x.split(',')) if pd.notna(x) else 0)
data_test['Bed Type'] = (data_test['Bed Type'] == 'Real Bed').astype(int)
data_test['Amenities'] = data_test['Amenities'].dropna().str.split(',').apply(len)
data_test['Features'] = data_test['Features'].dropna().str.split(',').apply(len)

# Mean Encoder
data_test['Property Type'] = group_property_type(data_test)
categorical = ['Neighbourhood Cleansed', 'Neighbourhood Group Cleansed', 'Property Type', 'Room Type']
for c in categorical:
    data_test[c] = data_test[c].map(mean_map[c])
    
# Ordinal Encoder
data_test['Cancellation Policy'] = data_test['Cancellation Policy'].replace(['super_strict_60', 'super_strict_30'], 'super_strict')
categories = [['flexible', 'moderate', 'strict', 'super_strict']]
ordinal_encoder = OrdinalEncoder(categories=categories)
data_test['Cancellation Policy'] = ordinal_encoder.fit_transform(data_test[['Cancellation Policy']])

# KNNImputer
X_imputed = imputer.fit_transform(data_test[columns_to_impute])
data_test_imputed = pd.DataFrame(X_imputed, columns=columns_to_impute,index=data_test.index)
data_test.update(data_test_imputed)


# Eliminamos más columnas del modelo (después de Lasso)
columns_to_drop_2 = ['Host Verifications', 'Stay Duration']
data_test = data_test.drop(columns_to_drop_2, axis=1)


# Eliminamos más columnas del modelo (tras el 2º análisis)
columns_to_drop_3 = ['Features','Bed Type','Cancellation Policy','Extra People','Neighbourhood Group Cleansed','Property Type']
data_test = data_test.drop(columns_to_drop_3, axis=1)


# Verificamos que no hay datos faltantes y que son características numéricas 
data_test.info()

<class 'pandas.core.frame.DataFrame'>
Index: 2619 entries, 0 to 2652
Data columns (total 17 columns):
 #   Column                  Non-Null Count  Dtype  
---  ------                  --------------  -----  
 0   Host Since              2619 non-null   float64
 1   Host Listings Count     2619 non-null   float64
 2   Neighbourhood Cleansed  2619 non-null   float64
 3   Room Type               2619 non-null   float64
 4   Accommodates            2619 non-null   int64  
 5   Bathrooms               2619 non-null   float64
 6   Bedrooms                2619 non-null   float64
 7   Beds                    2619 non-null   float64
 8   Amenities               2619 non-null   float64
 9   Price                   2619 non-null   float64
 10  Cleaning Fee            2619 non-null   float64
 11  Guests Included         2619 non-null   int64  
 12  LatLongInteraction      2619 non-null   float64
 13  BedsPerRoom             2619 non-null   float64
 14  BathsPerRoom            2619 non-null   float64
 15  PricePerBed             2619 non-null   float64
 16  BedBathRooms            2619 non-null   float64
dtypes: float64(15), int64(2)
memory usage: 368.3 KB


# Sacamos los datos de test
data_test_values = data_test.values
y_test = data_test_values[:, price_index]   
X_test = np.delete(data_test_values, price_index, axis=1)

feature_names_test = np.delete(data_test.columns.values, price_index)

# Esta normalización/escalado se realiza con el scaler anterior, basado en los datos de training!
XtestScaled = scaler.transform(X_test)


from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score

def compute_metrics(y_true, y_pred):
    metrics = {
        'MAE': round(mean_absolute_error(y_true, y_pred),3),
        'MSE': round(mean_squared_error(y_true, y_pred),3),
        'RMSE': round(mean_squared_error(y_true, y_pred, squared=False),3),
        'R2': round(r2_score(y_true, y_pred),3)
    }
    return metrics


from sklearn.linear_model import Lasso

n_alphas = 20
alphas = np.logspace(-10, 0, n_alphas)

coefs = []

norm2_coefs = []
for a in alphas:
    lasso = Lasso(alpha=a).fit(XtrainScaled, y_train)
    coefs.append(lasso.coef_)
    norm2_coefs.append(np.dot(lasso.coef_,lasso.coef_.T))

plt.figure(figsize=(14, 5))

ax = plt.subplot(1, 2, 1)
ax.plot(alphas, coefs)
ax.set_xscale('log')
ax.set_xlim(ax.get_xlim()[::-1])  # reverse axis
plt.xlabel('alpha')
plt.ylabel('$w_i$')
plt.title('Coeficientes en función de la regularización')
plt.axis('tight')


ax = plt.subplot(1, 2, 2)
ax.plot(alphas, norm2_coefs)
ax.set_xscale('log')
ax.set_xlim(ax.get_xlim()[::-1])  # reverse axis
plt.xlabel('alpha')
plt.ylabel('$||\mathbf{w}||^2_2$')
plt.title('Norma de los coeffs en función de la regularización')
plt.axis('tight')
plt.show()


from sklearn.model_selection import GridSearchCV

alpha_vector = np.logspace(-10,1,25)

param_grid = {'alpha': alpha_vector }
grid = GridSearchCV(Lasso(), scoring= 'neg_mean_squared_error', param_grid=param_grid, cv = 5)
grid.fit(XtrainScaled, y_train)
print("best parameters: {}".format(grid.best_params_))

scores = -1*np.array(grid.cv_results_['mean_test_score'])
plt.semilogx(alpha_vector,scores,'-o')
plt.xlabel('alpha',fontsize=16)
plt.ylabel('5-Fold MSE')
plt.ylim(min(scores) - 1, max(scores) + 1)
sns.despine(top=True, right=True, left=False, bottom=False)
plt.show()

best parameters: {'alpha': 0.01778279410038923}


lasso = Lasso(alpha=0.01778279410038923)  # Reemplazar con el valor de alpha anterior
lasso.fit(XtrainScaled, y_train)

# Obtener los coeficientes
lasso_coefs = lasso.coef_

# Identificar las características que el modelo Lasso ha reducido a cero
features_to_remove = [feature for feature, coef in zip(feature_names, lasso_coefs) if coef == 0]

print("Características para eliminar:", features_to_remove)

Características para eliminar: []


print("Train: ",lasso.score(XtrainScaled,y_train))
print("Test: ",lasso.score(XtestScaled,y_test))

Train:  0.8154816001821197
Test:  0.8252591851752692


y_pred = lasso.predict(XtestScaled)

# Métricas
metrics = compute_metrics(y_test, y_pred)

for metric_name, metric_value in metrics.items():
    print(f"{metric_name}: {metric_value}")

# Plotting the predicted vs actual values
plt.figure(figsize=(10, 6))
plt.scatter(y_test, y_pred, alpha=0.5)
plt.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], 'k--', lw=2)  # Diagonal line
plt.xlabel('Valores Reales')
plt.ylabel('Valores Predichos')
plt.title('Lasso Regression: Predicción vs Real')

plt.show()

MAE: 12.408
MSE: 505.83
RMSE: 22.491
R2: 0.825


# ElasticNetCV - maneja la multicolinealidad mejor que Lasso
from sklearn.linear_model import ElasticNetCV

enet = ElasticNetCV(cv=5, random_state=0).fit(XtrainScaled, y_train)
y_pred_enet = enet.predict(XtestScaled)

# Métricas
metrics = compute_metrics(y_test, y_pred)

for metric_name, metric_value in metrics.items():
    print(f"{metric_name}: {metric_value}")

MAE: 12.408
MSE: 505.83
RMSE: 22.491
R2: 0.825


print("Train: ",enet.score(XtrainScaled,y_train))
print("Test: ",enet.score(XtestScaled,y_test))

Train:  0.8156313565387212
Test:  0.825079800905857


from sklearn.linear_model import LinearRegression

# Entrenar el modelo de regresión lineal
lr = LinearRegression().fit(XtrainScaled, y_train)

# Hacer predicciones en el conjunto de prueba
y_pred = lr.predict(XtestScaled)

# Métricas
metrics = compute_metrics(y_test, y_pred)

for metric_name, metric_value in metrics.items():
    print(f"{metric_name}: {metric_value}")

# Mostrar los coeficientes del modelo
print('Intercepto (w0):', lr.intercept_)
print('Coeficientes (w1, w2, ..., wn):', lr.coef_)

# Calcular la norma L2 al cuadrado de los coeficientes (sin incluir el intercepto)
norm_w2 = np.dot(lr.coef_,lr.coef_.T) 
print(f'\n||w||_2^2 = {norm_w2:.2g}')

MAE: 12.415
MSE: 505.786
RMSE: 22.49
R2: 0.825
Intercepto (w0): 65.7782414023054
Coeficientes (w1, w2, ..., wn): [ -1.07012948  -0.31977824   2.93189686   1.32212255   2.40605079
   9.20571351   5.26664076   7.53438872   0.61977756  13.39736857
   2.54196563   0.56047219   5.18524856 -10.46423407  28.82881597
   7.73956604]

||w||_2^2 = 1.4e+03


print("Train: ",lr.score(XtrainScaled,y_train))
print("Test: ",lr.score(XtestScaled,y_test))

Train:  0.8154845311576571
Test:  0.8252743029936962


# Gráfico de predicciones vs valores reales
plt.scatter(y_test, y_pred)
plt.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], 'k--', lw=4)
plt.xlabel('Valores Reales')
plt.ylabel('Predicciones')
plt.title(f'Linear Regression: Valores Reales vs. Predicciones')
sns.despine(top=True, right=True, left=False, bottom=False)
plt.show()


residuos = y_test - y_pred

plt.figure(figsize=(10,6))
plt.scatter(y_pred, residuos, alpha=0.5)
plt.hlines(y=0, xmin=y_pred.min(), xmax=y_pred.max(), colors='red', linestyles='--')
plt.xlabel('Valores Predichos')
plt.ylabel('Residuos')
plt.title('Gráfico de Residuos')
sns.despine(top=True, right=True, left=False, bottom=False)
plt.show()


# Curva de Aprendizaje - Traza el error de validación cruzada en función del tamaño del conjunto de entrenamiento
from sklearn.model_selection import learning_curve

train_sizes, train_scores, valid_scores = learning_curve(
    LinearRegression(), XtrainScaled, y_train, train_sizes=np.linspace(0.01, 1.0, 40), cv=5,
    scoring="neg_root_mean_squared_error")
train_errors = -train_scores.mean(axis=1)
valid_errors = -valid_scores.mean(axis=1)

plt.plot(train_sizes, train_errors, "r-+", linewidth=2, label="train")
plt.plot(train_sizes, valid_errors, "b-", linewidth=2, label="valid")
plt.xlabel('Tamaño del conjunto de entrenamiento')
plt.ylabel('MSE')
plt.title('Curva de aprendizaje')
plt.legend()
sns.despine(top=True, right=True, left=False, bottom=False)
plt.show()


from sklearn.tree import DecisionTreeRegressor

maxDepth = range(1,12)
param_grid = {'max_depth': maxDepth }
grid = GridSearchCV(DecisionTreeRegressor(random_state=0), param_grid=param_grid, cv = 3, verbose=2)
grid.fit(XtrainScaled, y_train)
print("best mean cross-validation score: {:.3f}".format(grid.best_score_))
print("best parameters: {}".format(grid.best_params_))

scores = np.array(grid.cv_results_['mean_test_score'])
plt.plot(maxDepth,scores,'-o')
plt.xlabel('max_depth',fontsize=16)
plt.ylabel('10-Fold MSE')
#plt.ylim((-1, 0))
sns.despine(top=True, right=True, left=False, bottom=False)
plt.show()

Fitting 3 folds for each of 11 candidates, totalling 33 fits
[CV] END ........................................max_depth=1; total time=   0.0s
[CV] END ........................................max_depth=1; total time=   0.0s
[CV] END ........................................max_depth=1; total time=   0.0s
[CV] END ........................................max_depth=2; total time=   0.0s
[CV] END ........................................max_depth=2; total time=   0.0s
[CV] END ........................................max_depth=2; total time=   0.0s
[CV] END ........................................max_depth=3; total time=   0.0s
[CV] END ........................................max_depth=3; total time=   0.0s
[CV] END ........................................max_depth=3; total time=   0.0s
[CV] END ........................................max_depth=4; total time=   0.0s
[CV] END ........................................max_depth=4; total time=   0.0s
[CV] END ........................................max_depth=4; total time=   0.0s
[CV] END ........................................max_depth=5; total time=   0.0s
[CV] END ........................................max_depth=5; total time=   0.0s
[CV] END ........................................max_depth=5; total time=   0.0s
[CV] END ........................................max_depth=6; total time=   0.0s
[CV] END ........................................max_depth=6; total time=   0.0s
[CV] END ........................................max_depth=6; total time=   0.0s
[CV] END ........................................max_depth=7; total time=   0.0s
[CV] END ........................................max_depth=7; total time=   0.0s
[CV] END ........................................max_depth=7; total time=   0.0s
[CV] END ........................................max_depth=8; total time=   0.0s
[CV] END ........................................max_depth=8; total time=   0.0s
[CV] END ........................................max_depth=8; total time=   0.0s
[CV] END ........................................max_depth=9; total time=   0.0s
[CV] END ........................................max_depth=9; total time=   0.0s
[CV] END ........................................max_depth=9; total time=   0.0s
[CV] END .......................................max_depth=10; total time=   0.0s
[CV] END .......................................max_depth=10; total time=   0.0s
[CV] END .......................................max_depth=10; total time=   0.0s
[CV] END .......................................max_depth=11; total time=   0.1s
[CV] END .......................................max_depth=11; total time=   0.1s
[CV] END .......................................max_depth=11; total time=   0.1s
best mean cross-validation score: 0.855
best parameters: {'max_depth': 11}


from sklearn import tree

treeModel = DecisionTreeRegressor(max_depth=10).fit(XtrainScaled, y_train)

fig = plt.figure(figsize=(25,20))
_ = tree.plot_tree(treeModel, feature_names=list(feature_names), filled=True)


importances = treeModel.feature_importances_
importances = importances / np.max(importances)

indices = np.argsort(importances)[::-1]

sns.set_theme(style="white")
plt.figure(figsize=(8,5))
plt.barh(range(XtrainScaled.shape[1]),importances[indices])
plt.yticks(range(XtrainScaled.shape[1]),feature_names[indices])
sns.despine(top=True, right=True, left=False, bottom=False)
plt.show()


# Evaluación del Árbol de Decisión
maxDepthOptimo = 11
treeModel = DecisionTreeRegressor(max_depth=maxDepthOptimo).fit(XtrainScaled,y_train)

print("Train: ",treeModel.score(XtrainScaled,y_train))
print("Test: ",treeModel.score(XtestScaled,y_test))

Train:  0.9971661476137205
Test:  0.9565759431334919


y_pred = treeModel.predict(XtestScaled)

# Métricas
metrics = compute_metrics(y_test, y_pred)

for metric_name, metric_value in metrics.items():
    print(f"{metric_name}: {metric_value}")

plt.figure(figsize=(8, 6))
plt.scatter(y_test, y_pred, alpha=0.5)
plt.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], 'k--', lw=4)  # Línea de perfecta predicción
plt.xlabel('Valores Reales')
plt.ylabel('Predicciones')
plt.title('Tree Model: Valores Reales vs. Predicciones')
sns.despine(top=True, right=True, left=False, bottom=False)
plt.show()

MAE: 2.72
MSE: 110.83
RMSE: 10.528
R2: 0.962


# Curva de Aprendizaje
train_sizes, train_scores, valid_scores = learning_curve(
    treeModel, XtrainScaled, y_train, train_sizes=np.linspace(0.01, 1.0, 40), cv=5,
    scoring="neg_root_mean_squared_error")
train_errors = -train_scores.mean(axis=1)
valid_errors = -valid_scores.mean(axis=1)

plt.plot(train_sizes, train_errors, "r-+", linewidth=2, label="train")
plt.plot(train_sizes, valid_errors, "b-", linewidth=2, label="valid")
plt.xlabel('Tamaño del conjunto de entrenamiento')
plt.ylabel('RMSE')
plt.title('Curva de aprendizaje')
plt.legend()
sns.despine(top=True, right=True, left=False, bottom=False)
plt.show()


from sklearn.ensemble import RandomForestRegressor

maxDepth = range(1,15)
tuned_parameters = {'max_depth': maxDepth}

grid = GridSearchCV(
    RandomForestRegressor(random_state=0, n_estimators=200, max_features='sqrt'), 
    param_grid=tuned_parameters, cv=3, verbose=2) 

grid.fit(XtrainScaled, y_train)

print("best mean cross-validation score: {:.3f}".format(grid.best_score_))
print("best parameters: {}".format(grid.best_params_))

scores = np.array(grid.cv_results_['mean_test_score'])
plt.plot(maxDepth,scores,'-o')
plt.xlabel('max_depth')
plt.ylabel('10-fold ACC')
sns.despine(top=True, right=True, left=False, bottom=False)
plt.show()

Fitting 3 folds for each of 14 candidates, totalling 42 fits
[CV] END ........................................max_depth=1; total time=   0.3s
[CV] END ........................................max_depth=1; total time=   0.3s
[CV] END ........................................max_depth=1; total time=   0.3s
[CV] END ........................................max_depth=2; total time=   0.5s
[CV] END ........................................max_depth=2; total time=   0.5s
[CV] END ........................................max_depth=2; total time=   0.5s
[CV] END ........................................max_depth=3; total time=   0.6s
[CV] END ........................................max_depth=3; total time=   0.6s
[CV] END ........................................max_depth=3; total time=   0.6s
[CV] END ........................................max_depth=4; total time=   0.7s
[CV] END ........................................max_depth=4; total time=   0.7s
[CV] END ........................................max_depth=4; total time=   0.7s
[CV] END ........................................max_depth=5; total time=   0.9s
[CV] END ........................................max_depth=5; total time=   0.9s
[CV] END ........................................max_depth=5; total time=   1.0s
[CV] END ........................................max_depth=6; total time=   1.0s
[CV] END ........................................max_depth=6; total time=   1.1s
[CV] END ........................................max_depth=6; total time=   1.0s
[CV] END ........................................max_depth=7; total time=   1.2s
[CV] END ........................................max_depth=7; total time=   1.2s
[CV] END ........................................max_depth=7; total time=   1.2s
[CV] END ........................................max_depth=8; total time=   1.4s
[CV] END ........................................max_depth=8; total time=   1.3s
[CV] END ........................................max_depth=8; total time=   1.3s
[CV] END ........................................max_depth=9; total time=   1.4s
[CV] END ........................................max_depth=9; total time=   1.5s
[CV] END ........................................max_depth=9; total time=   1.4s
[CV] END .......................................max_depth=10; total time=   1.6s
[CV] END .......................................max_depth=10; total time=   1.6s
[CV] END .......................................max_depth=10; total time=   1.6s
[CV] END .......................................max_depth=11; total time=   1.8s
[CV] END .......................................max_depth=11; total time=   1.7s
[CV] END .......................................max_depth=11; total time=   1.7s
[CV] END .......................................max_depth=12; total time=   1.9s
[CV] END .......................................max_depth=12; total time=   1.9s
[CV] END .......................................max_depth=12; total time=   1.9s
[CV] END .......................................max_depth=13; total time=   2.0s
[CV] END .......................................max_depth=13; total time=   2.1s
[CV] END .......................................max_depth=13; total time=   2.0s
[CV] END .......................................max_depth=14; total time=   2.1s
[CV] END .......................................max_depth=14; total time=   2.2s
[CV] END .......................................max_depth=14; total time=   2.1s
best mean cross-validation score: 0.898
best parameters: {'max_depth': 14}


maxDepthOptimo = grid.best_params_['max_depth']
randomForest = RandomForestRegressor(max_depth=maxDepthOptimo,n_estimators=200,max_features='sqrt').fit(XtrainScaled,y_train)

importances = randomForest.feature_importances_
importances = importances / np.max(importances)

indices = np.argsort(importances)[::-1]

sns.set_theme(style="white")
plt.figure(figsize=(8,5))
plt.barh(range(XtrainScaled.shape[1]),importances[indices])
plt.yticks(range(XtrainScaled.shape[1]),feature_names[indices])
sns.despine(top=True, right=True, left=False, bottom=False)
plt.show()


for score, name in zip(randomForest.feature_importances_, feature_names):
    print(round(score,2), name)

0.02 Host Since
0.01 Host Listings Count
0.03 Neighbourhood Cleansed
0.07 Room Type
0.07 Accommodates
0.05 Bathrooms
0.08 Bedrooms
0.05 Beds
0.01 Amenities
0.19 Cleaning Fee
0.02 Guests Included
0.02 LatLongInteraction
0.02 BedsPerRoom
0.01 BathsPerRoom
0.23 PricePerBed
0.13 BedBathRooms


# Evaluación de Random Forest
maxDepthOptimo = grid.best_params_['max_depth']
randomForest = RandomForestRegressor(max_depth=maxDepthOptimo,n_estimators=200,max_features='sqrt').fit(XtrainScaled,y_train)

print("Train: ",randomForest.score(XtrainScaled,y_train))
print("Test: ",randomForest.score(XtestScaled,y_test))

Train:  0.9831833465915698
Test:  0.9438753933446635


y_pred = randomForest.predict(XtestScaled)

# Métricas
metrics = compute_metrics(y_test, y_pred)

for metric_name, metric_value in metrics.items():
    print(f"{metric_name}: {metric_value}")

plt.figure(figsize=(8, 6))
plt.scatter(y_test, y_pred, alpha=0.5)
plt.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], 'k--', lw=4)  # Línea de perfecta predicción
plt.xlabel('Valores Reales')
plt.ylabel('Predicciones')
plt.title(f'Valores Reales vs. Predicciones')
sns.despine(top=True, right=True, left=False, bottom=False)
plt.show()

MAE: 5.818
MSE: 162.466
RMSE: 12.746
R2: 0.944


# Curva de Aprendizaje
train_sizes, train_scores, valid_scores = learning_curve(
    randomForest, XtrainScaled, y_train, train_sizes=np.linspace(0.01, 1.0, 40), cv=5,
    scoring="neg_root_mean_squared_error")
train_errors = -train_scores.mean(axis=1)
valid_errors = -valid_scores.mean(axis=1)

plt.plot(train_sizes, train_errors, "r-+", linewidth=2, label="train")
plt.plot(train_sizes, valid_errors, "b-", linewidth=2, label="valid")
plt.xlabel('Tamaño del conjunto de entrenamiento')
plt.ylabel('RMSE')
plt.title('Curva de aprendizaje')
plt.legend()
sns.despine(top=True, right=True, left=False, bottom=False)
plt.show()


from sklearn.ensemble import BaggingRegressor

maxDepth = range(1,15)
tuned_parameters = {'base_estimator__max_depth': maxDepth}

grid = GridSearchCV(
    BaggingRegressor(estimator=DecisionTreeRegressor(), random_state=0, n_estimators=200), 
    param_grid=tuned_parameters, cv=3, verbose=2) 

grid.fit(XtrainScaled, y_train)

print("best mean cross-validation score: {:.3f}".format(grid.best_score_))
print("best parameters: {}".format(grid.best_params_))

scores = np.array(grid.cv_results_['mean_test_score'])
plt.plot(maxDepth,scores,'-o')
plt.xlabel('max_depth')
plt.ylabel('10-fold ACC')
sns.despine(top=True, right=True, left=False, bottom=False)
plt.show()

Fitting 3 folds for each of 14 candidates, totalling 42 fits

/Users/rociobenitezgarcia/anaconda3/lib/python3.11/site-packages/sklearn/model_selection/_validation.py:720: FutureWarning: Parameter 'base_estimator' of BaggingRegressor is deprecated in favor of 'estimator'. See BaggingRegressor's docstring for more details.
  estimator = estimator.set_params(**cloned_parameters)

[CV] END ........................base_estimator__max_depth=1; total time=   0.8s

/Users/rociobenitezgarcia/anaconda3/lib/python3.11/site-packages/sklearn/model_selection/_validation.py:720: FutureWarning: Parameter 'base_estimator' of BaggingRegressor is deprecated in favor of 'estimator'. See BaggingRegressor's docstring for more details.
  estimator = estimator.set_params(**cloned_parameters)

[CV] END ........................base_estimator__max_depth=1; total time=   0.9s

/Users/rociobenitezgarcia/anaconda3/lib/python3.11/site-packages/sklearn/model_selection/_validation.py:720: FutureWarning: Parameter 'base_estimator' of BaggingRegressor is deprecated in favor of 'estimator'. See BaggingRegressor's docstring for more details.
  estimator = estimator.set_params(**cloned_parameters)

[CV] END ........................base_estimator__max_depth=1; total time=   0.8s

/Users/rociobenitezgarcia/anaconda3/lib/python3.11/site-packages/sklearn/model_selection/_validation.py:720: FutureWarning: Parameter 'base_estimator' of BaggingRegressor is deprecated in favor of 'estimator'. See BaggingRegressor's docstring for more details.
  estimator = estimator.set_params(**cloned_parameters)

[CV] END ........................base_estimator__max_depth=2; total time=   1.3s

/Users/rociobenitezgarcia/anaconda3/lib/python3.11/site-packages/sklearn/model_selection/_validation.py:720: FutureWarning: Parameter 'base_estimator' of BaggingRegressor is deprecated in favor of 'estimator'. See BaggingRegressor's docstring for more details.
  estimator = estimator.set_params(**cloned_parameters)


# Evaluación de Baging Regressor
maxDepthOptimo = grid.best_params_['base_estimator__max_depth']
#maxDepthOptimo = 9
baggingModel = BaggingRegressor(estimator=DecisionTreeRegressor(max_depth=maxDepthOptimo),n_estimators=200).fit(XtrainScaled,y_train)

print("Train: ", baggingModel.score(XtrainScaled,y_train))
print("Test: ", baggingModel.score(XtestScaled,y_test))

Train:  0.992663296332992
Test:  0.9752735476497003


importances = np.mean([tree.feature_importances_ for tree in baggingModel.estimators_], axis=0)
importances = importances / np.max(importances)

indices = np.argsort(importances)[::-1]

sns.set_theme(style="white")
plt.figure(figsize=(8,5))
plt.barh(range(XtrainScaled.shape[1]),importances[indices])
plt.yticks(range(XtrainScaled.shape[1]),feature_names[indices])
sns.despine(top=True, right=True, left=False, bottom=False)
plt.show()


y_pred = baggingModel.predict(XtestScaled)

# Métricas
metrics = compute_metrics(y_test, y_pred)

for metric_name, metric_value in metrics.items():
    print(f"{metric_name}: {metric_value}")

plt.figure(figsize=(8, 6))
plt.scatter(y_test, y_pred, alpha=0.5)
plt.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], 'k--', lw=4)  # Línea de perfecta predicción
plt.xlabel('Valores Reales')
plt.ylabel('Predicciones')
plt.title(f'Valores Reales vs. Predicciones')
sns.despine(top=True, right=True, left=False, bottom=False)
plt.show()

MAE: 1.572
MSE: 71.577
RMSE: 8.46
R2: 0.975


# Curva de Aprendizaje
train_sizes, train_scores, valid_scores = learning_curve(
    baggingModel, XtrainScaled, y_train, train_sizes=np.linspace(0.01, 1.0, 40), cv=5,
    scoring="neg_root_mean_squared_error")
train_errors = -train_scores.mean(axis=1)
valid_errors = -valid_scores.mean(axis=1)

plt.plot(train_sizes, train_errors, "r-+", linewidth=2, label="train")
plt.plot(train_sizes, valid_errors, "b-", linewidth=2, label="valid")
plt.xlabel('Tamaño del conjunto de entrenamiento')
plt.ylabel('RMSE')
plt.title('Curva de aprendizaje')
plt.legend()
sns.despine(top=True, right=True, left=False, bottom=False)
plt.show()


from sklearn.ensemble import GradientBoostingRegressor

Niterations = [500, 1000, 1500, 2000]
learningRate = [0.1, 0.05]
# mantenemos max_depth estático: max_depth=3

param_grid = {'n_estimators': Niterations,'learning_rate':learningRate }

grid = GridSearchCV(
    GradientBoostingRegressor(random_state = 0, max_depth = 3), 
    param_grid=param_grid, cv = 5, verbose = 2)

grid.fit(X_train, y_train)
print("best mean cross-validation score: {:.3f}".format(grid.best_score_))
print("best parameters: {}".format(grid.best_params_))

Fitting 5 folds for each of 8 candidates, totalling 40 fits
[CV] END ................learning_rate=0.1, n_estimators=500; total time=   8.0s
[CV] END ................learning_rate=0.1, n_estimators=500; total time=   8.2s
[CV] END ................learning_rate=0.1, n_estimators=500; total time=   8.2s
[CV] END ................learning_rate=0.1, n_estimators=500; total time=   8.1s
[CV] END ................learning_rate=0.1, n_estimators=500; total time=   8.1s
[CV] END ...............learning_rate=0.1, n_estimators=1000; total time=  15.9s
[CV] END ...............learning_rate=0.1, n_estimators=1000; total time=  16.0s
[CV] END ...............learning_rate=0.1, n_estimators=1000; total time=  15.8s
[CV] END ...............learning_rate=0.1, n_estimators=1000; total time=  15.8s
[CV] END ...............learning_rate=0.1, n_estimators=1000; total time=  16.3s
[CV] END ...............learning_rate=0.1, n_estimators=1500; total time=  24.1s
[CV] END ...............learning_rate=0.1, n_estimators=1500; total time=  24.3s
[CV] END ...............learning_rate=0.1, n_estimators=1500; total time=  24.0s
[CV] END ...............learning_rate=0.1, n_estimators=1500; total time=  23.8s
[CV] END ...............learning_rate=0.1, n_estimators=1500; total time=  24.1s
[CV] END ...............learning_rate=0.1, n_estimators=2000; total time=  31.7s
[CV] END ...............learning_rate=0.1, n_estimators=2000; total time=  31.6s
[CV] END ...............learning_rate=0.1, n_estimators=2000; total time=  32.1s
[CV] END ...............learning_rate=0.1, n_estimators=2000; total time=  31.5s
[CV] END ...............learning_rate=0.1, n_estimators=2000; total time=  31.8s
[CV] END ...............learning_rate=0.05, n_estimators=500; total time=   8.0s
[CV] END ...............learning_rate=0.05, n_estimators=500; total time=   7.9s
[CV] END ...............learning_rate=0.05, n_estimators=500; total time=   7.9s
[CV] END ...............learning_rate=0.05, n_estimators=500; total time=   8.2s
[CV] END ...............learning_rate=0.05, n_estimators=500; total time=   7.9s
[CV] END ..............learning_rate=0.05, n_estimators=1000; total time=  16.1s
[CV] END ..............learning_rate=0.05, n_estimators=1000; total time=  16.0s
[CV] END ..............learning_rate=0.05, n_estimators=1000; total time=  15.9s
[CV] END ..............learning_rate=0.05, n_estimators=1000; total time=  16.3s
[CV] END ..............learning_rate=0.05, n_estimators=1000; total time=  16.0s
[CV] END ..............learning_rate=0.05, n_estimators=1500; total time=  23.8s
[CV] END ..............learning_rate=0.05, n_estimators=1500; total time=  24.2s
[CV] END ..............learning_rate=0.05, n_estimators=1500; total time=  23.8s
[CV] END ..............learning_rate=0.05, n_estimators=1500; total time=  24.1s
[CV] END ..............learning_rate=0.05, n_estimators=1500; total time=  24.1s
[CV] END ..............learning_rate=0.05, n_estimators=2000; total time=  32.1s
[CV] END ..............learning_rate=0.05, n_estimators=2000; total time=  32.0s
[CV] END ..............learning_rate=0.05, n_estimators=2000; total time=  31.8s
[CV] END ..............learning_rate=0.05, n_estimators=2000; total time=  31.7s
[CV] END ..............learning_rate=0.05, n_estimators=2000; total time=  31.8s
best mean cross-validation score: 0.982
best parameters: {'learning_rate': 0.1, 'n_estimators': 2000}


# Gradient Boosting Regressor
lrOptimo = grid.best_params_['learning_rate']
neOptimo = grid.best_params_['n_estimators']
bt = GradientBoostingRegressor(random_state=0, max_depth=3,learning_rate=lrOptimo, n_estimators=neOptimo)
bt.fit(XtrainScaled,y_train)

error = 1-grid.cv_results_['mean_test_score'].reshape(len(learningRate),len(Niterations))
colors = ['r','b','g','k','m']
for i,lr in enumerate(learningRate):    
    plt.plot(Niterations,error[i,:],colors[i] + '--o',label='lr = %g'%lr)

plt.legend()
plt.xlabel('Iteraciones')
plt.ylabel('5-fold CV Error')
plt.title('train: %0.3f\ntest:  %0.3f'%(bt.score(XtrainScaled,y_train),bt.score(XtestScaled,y_test)))
sns.despine(top=True, right=True, left=False, bottom=False)
plt.grid()
plt.show()


print("Train: ", bt.score(XtrainScaled,y_train))
print("Test: ", bt.score(XtestScaled,y_test))

Train:  0.9997283072534239
Test:  0.9947365442926436


y_pred = bt.predict(XtestScaled)

# Métricas
metrics = compute_metrics(y_test, y_pred)

for metric_name, metric_value in metrics.items():
    print(f"{metric_name}: {metric_value}")

plt.figure(figsize=(8, 6))
plt.scatter(y_test, y_pred, alpha=0.5)
plt.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], 'k--', lw=4)  # Línea de perfecta predicción
plt.xlabel('Valores Reales')
plt.ylabel('Predicciones')
plt.title(f'Valores Reales vs. Predicciones')
sns.despine(top=True, right=True, left=False, bottom=False)
plt.show()

MAE: 1.165
MSE: 15.236
RMSE: 3.903
R2: 0.995


# Curva de Aprendizaje
train_sizes, train_scores, valid_scores = learning_curve(
    bt, XtrainScaled, y_train, train_sizes=np.linspace(0.01, 1.0, 40), cv=5,
    scoring="neg_root_mean_squared_error")
train_errors = -train_scores.mean(axis=1)
valid_errors = -valid_scores.mean(axis=1)

plt.plot(train_sizes, train_errors, "r-+", linewidth=2, label="train")
plt.plot(train_sizes, valid_errors, "b-", linewidth=2, label="valid")
plt.xlabel('Tamaño del conjunto de entrenamiento')
plt.ylabel('RMSE')
plt.title('Curva de aprendizaje')
plt.legend()
sns.despine(top=True, right=True, left=False, bottom=False)
plt.show()


from sklearn.svm import SVR

vectorC = np.logspace(-2, 2, 10)
vectorG = np.logspace(-5, 1, 8)

param_grid = {'C': vectorC, 'gamma': vectorG}
grid = GridSearchCV(SVR(kernel='rbf'), param_grid=param_grid, cv = 5, verbose=1)
grid.fit(XtrainScaled, y_train)

Fitting 5 folds for each of 80 candidates, totalling 400 fits

GridSearchCV(cv=5, estimator=SVR(),
             param_grid={'C': array([1.00000000e-02, 2.78255940e-02, 7.74263683e-02, 2.15443469e-01,
       5.99484250e-01, 1.66810054e+00, 4.64158883e+00, 1.29154967e+01,
       3.59381366e+01, 1.00000000e+02]),
                         'gamma': array([1.00000000e-05, 7.19685673e-05, 5.17947468e-04, 3.72759372e-03,
       2.68269580e-02, 1.93069773e-01, 1.38949549e+00, 1.00000000e+01])},
             verbose=1)

GridSearchCV(cv=5, estimator=SVR(),
             param_grid={'C': array([1.00000000e-02, 2.78255940e-02, 7.74263683e-02, 2.15443469e-01,
       5.99484250e-01, 1.66810054e+00, 4.64158883e+00, 1.29154967e+01,
       3.59381366e+01, 1.00000000e+02]),
                         'gamma': array([1.00000000e-05, 7.19685673e-05, 5.17947468e-04, 3.72759372e-03,
       2.68269580e-02, 1.93069773e-01, 1.38949549e+00, 1.00000000e+01])},
             verbose=1)

SVR()

SVR()


print("best mean cross-validation score: {:.3f}".format(grid.best_score_))
print("best parameters: {}".format(grid.best_params_))

# Mostramos prestaciones en CV
scores = grid.cv_results_['mean_test_score'].reshape(len(vectorC),len(vectorG))

plt.figure(figsize=(10,6))
plt.imshow(scores, interpolation='nearest', vmin= 0.6, vmax=0.9)
plt.xlabel('log(gamma)')
plt.ylabel('log(C)')
plt.colorbar()
plt.xticks(np.arange(len(vectorG)), np.log10(vectorG), rotation=90)
plt.yticks(np.arange(len(vectorC)), np.log10(vectorC))
plt.title('5-fold accuracy')
plt.show()

best mean cross-validation score: 0.927
best parameters: {'C': 100.0, 'gamma': 0.003727593720314938}


Copt = grid.best_params_['C']
Gopt = grid.best_params_['gamma']

svmModel = SVR(kernel='rbf',gamma = Gopt, C = Copt).fit(XtrainScaled,y_train)
print('Acc (TEST): %0.2f'%svmModel.score(XtestScaled,y_test))

Acc (TEST): 0.96


# Predicción
y_pred = svmModel.predict(XtestScaled)

# Métricas
metrics = compute_metrics(y_test, y_pred)

for metric_name, metric_value in metrics.items():
    print(f"{metric_name}: {metric_value}")

plt.scatter(y_test, y_pred, color='mediumaquamarine', label='SVMs Predictions')
plt.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], 'k--', lw=2)  # Línea de identidad
plt.title(f'Valores Reales vs Predicciones')
plt.xlabel('Valores Reales')
plt.ylabel('Predicciones')
plt.legend()
sns.despine(top=True, right=True, left=False, bottom=False)
plt.show()

MAE: 4.121
MSE: 116.13
RMSE: 10.776
R2: 0.96


print("Train: ", svmModel.score(XtrainScaled,y_train))
print("Test: ", svmModel.score(XtestScaled,y_test))

Train:  0.9466135230762418
Test:  0.9598823359046609


from sklearn.kernel_ridge import KernelRidge

# Definimos y entrenamos el modelo
kr = GridSearchCV(
    KernelRidge(kernel="rbf", gamma=0.1),
    param_grid={"alpha": [1e0, 0.1, 1e-2, 1e-3], "gamma": np.logspace(-2, 2, 5)},
)

kr.fit(XtrainScaled, y_train)

# Mejores parámetros y mejor puntuación
print("Mejores parámetros:", kr.best_params_)
print("Mejor puntuación (neg_mean_squared_error):", kr.best_score_)

kr_best = kr.best_estimator_

# Predicción
y_pred = kr.predict(XtestScaled)

# Métricas
metrics = compute_metrics(y_test, y_pred)

for metric_name, metric_value in metrics.items():
    print(f"{metric_name}: {metric_value}")

plt.scatter(y_test, y_pred, color='mediumaquamarine', label='Kernel Ridge Predictions')
plt.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], 'k--', lw=2)  # Línea de identidad
plt.title(f'Valores Reales vs Predicciones')
plt.xlabel('Valores Reales')
plt.ylabel('Predicciones')
plt.legend()
sns.despine(top=True, right=True, left=False, bottom=False)
plt.show()

Mejores parámetros: {'alpha': 0.001, 'gamma': 0.01}
Mejor puntuación (neg_mean_squared_error): 0.9747203739235382
MAE: 0.61
MSE: 6.214
RMSE: 2.493
R2: 0.998


print("Train: ", kr.score(XtrainScaled,y_train))
print("Test: ", kr.score(XtestScaled,y_test))

Train:  0.9990038605388917
Test:  0.9978534759363776


lr = LinearRegression().fit(XtrainScaled, y_train)
models = [lr, treeModel, randomForest, baggingModel, bt, svmModel, kr]
model_names = ['Linear Regression', 'Decision Tree', 'Random Forest', 'Bagging', 'Boosting', 'SVM', 'KRidge']

# Entrenar y predecir con cada modelo
predictions = {}
for model, name in zip(models, model_names):
    model.fit(XtrainScaled, y_train) 
    predictions[name] = model.predict(XtestScaled)

ncols = 2 # Nº de columnas para subplot
nrows = (len(models) + ncols - 1) // ncols # Nº de filas calculado en base a la cantidad de modelos y el nº de columnas

# Crear una figura y ejes para subplots
fig, axs = plt.subplots(nrows, ncols, figsize=(10, 4 * nrows))
axs = axs.ravel()  # Convertir la matriz de ejes en un array 1D para una fácil iteración

# Trazar cada modelo en su propio subplot y calcular métricas
for idx, (name, y_pred) in enumerate(predictions.items()):
    metrics = compute_metrics(y_test, y_pred)
    metric_text = "\n".join([f"{metric_name}: {metric_value:.2f}" for metric_name, metric_value in metrics.items()])
    
    # Trazar predicciones vs valores reales
    axs[idx].scatter(y_test, y_pred, alpha=0.3)
    axs[idx].plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], 'k--', lw=2)
    axs[idx].set_title(f'{name}\n{metric_text}', fontsize='9')
    axs[idx].set_xlabel('Valores Reales', fontsize='9')
    axs[idx].set_ylabel('Predicciones', fontsize='9')

plt.tight_layout()
plt.show()


from sklearn.model_selection import learning_curve

def plot_learning_curve(model, XtrainScaled, y_train, ax, model_name):
    train_sizes, train_scores, test_scores = learning_curve(
        model, XtrainScaled, y_train, train_sizes=np.linspace(0.1, 1.0, 10), cv=5, scoring='neg_mean_squared_error'
    )
    
    # Calcula la media y el intervalo de confianza del score de entrenamiento y de prueba para cada tamaño de conjunto de entrenamiento
    train_scores_mean = -np.mean(train_scores, axis=1)
    train_scores_std = np.std(train_scores, axis=1)
    test_scores_mean = -np.mean(test_scores, axis=1)
    test_scores_std = np.std(test_scores, axis=1)
    
    # Grafica las curvas de aprendizaje
    ax.plot(train_sizes, train_scores_mean, 'o-', color="r", label="Training score")
    ax.plot(train_sizes, test_scores_mean, 'o-', color="g", label="Cross-validation score")
    
    # Rellena entre las desviaciones estándar
    ax.fill_between(train_sizes, train_scores_mean - train_scores_std,
                    train_scores_mean + train_scores_std, alpha=0.1, color="r")
    ax.fill_between(train_sizes, test_scores_mean - test_scores_std,
                    test_scores_mean + test_scores_std, alpha=0.1, color="g")
    
    # Etiquetas y leyendas
    ax.set_title('Curva de aprendizaje: ' + model_name)
    ax.set_xlabel('Tamaño del conjunto de entrenamiento')
    ax.set_ylabel('MSE Negativo')
    ax.legend(loc="best")

# Crea una figura para graficar
fig, axes = plt.subplots(3, 2, figsize=(15, 15))  # Ajusta según la cantidad de modelos que tienes

# Lista de modelos a evaluar
models = [
    (lr, 'Regresión Lineal'),
    (treeModel, 'Árbol de Decisión'),
    (randomForest, 'Random Forest'),
    (baggingModel, 'Bagging'),
    (bt, 'Boosting'),
    (svmModel, 'SVM'),
    (kr, 'kRidge')
]

# Grafica las curvas de aprendizaje de cada modelo
for ax, (model, name) in zip(axes.flatten(), models):
    plot_learning_curve(model, XtrainScaled, y_train, ax, name)

plt.tight_layout()
plt.show()

	0	1	2	3	4
ID	13448215	1046926	11633315	16801780	8667962
Listing Url	https://www.airbnb.com/rooms/13448215	https://www.airbnb.com/rooms/1046926	https://www.airbnb.com/rooms/11633315	https://www.airbnb.com/rooms/16801780	https://www.airbnb.com/rooms/8667962
Scrape ID	20170407214119	20170407214119	20170407214119	20170407214119	20170407214119
Last Scraped	2017-04-08	2017-04-08	2017-04-08	2017-04-08	2017-04-08
Name	Luxury Room Madrid Retiro Wifi	Single room in Madrid - WIFI	Apartment a step away from Gran Vía	Habitación doble en Lavapies	Comfortable Small Room & Private Bathroom- Cen...
Summary	This is a new 100sqm 2 bedroom apartment locat...	Single room in cozy apartment with 4 bedrooms ...	Wonderful apartment in the centre of Madrid, n...	Habitación doble con vistas al jardín del conv...	Confortable room for 1 but can allow up to 2 p...
Space	It's a master room with a 160cm real bed with ...	One single room for rent in a spacious apartme...	It´s on first floor. A very cozy and quiet apa...	El piso consta de dos habitaciones, un salón, ...	El apartamento es muy acogedor, luminoso, sile...
Description	This is a new 100sqm 2 bedroom apartment locat...	Single room in cozy apartment with 4 bedrooms ...	Wonderful apartment in the centre of Madrid, n...	Habitación doble con vistas al jardín del conv...	Confortable room for 1 but can allow up to 2 p...
Experiences Offered	none	none	none	none	none
Neighborhood Overview	The neighborhood is located in the city center...	La zona es tranquila y muy apropiada para los ...	Palacio neighborhood. A marvellous touristic a...	El barrio de Lavapies es único, por su ambient...	La zona es genial. Además de estar cerca de to...
Notes	I love non-smoking, respectful guests. No part...	NaN	NaN	Precio habitación doble (1 huésped): 30€ Preci...	El Carrefour Express que está al lado está muy...
Transit	It's very convenient to move around by bus or ...	El piso se encuentra a 10 min andando de la es...	Plaza de España metro station at only a few se...	Dispones a 2 minutos del metro de Lavapies, y ...	Tienes a dos minutos andando las líneas 2, 3 y...
Access	AC, heating, hot water. Fully equipped kitchen...	La cocina y el comedor, así como todos sus ute...	We speak perfect English, and we would be deli...	Durante tu alojamiento puedes disponer de todo...	Del apartamento puedes usar: El comedor para d...
Interaction	Landlord has quite a busy working schedule but...	Me gusta tener una relacion cercana con los in...	We speak perfect English, and we would be deli...	Por supuesto es que estaré disponible por si m...	Nosotros te recibiremos personalmente en nuest...
House Rules	- No smoking, no parties, respectful with neig...	Ninguna norma que impida sentirse cómodo en la...	Our main rule is that you make yourself feel a...	Vivo en casa con Fiona, una gata Maine Coon mu...	Somos una pareja tranquila que valora muchísim...
Thumbnail Url	NaN	https://a0.muscache.com/im/pictures/866cfc5e-f...	https://a0.muscache.com/im/pictures/f13148ba-c...	https://a0.muscache.com/im/pictures/c8acf003-1...	https://a0.muscache.com/im/pictures/ccc118e5-8...
Medium Url	NaN	https://a0.muscache.com/im/pictures/866cfc5e-f...	https://a0.muscache.com/im/pictures/f13148ba-c...	https://a0.muscache.com/im/pictures/c8acf003-1...	https://a0.muscache.com/im/pictures/ccc118e5-8...
Picture Url	https://public.opendatasoft.com/api/v2/catalog...	https://public.opendatasoft.com/api/v2/catalog...	https://public.opendatasoft.com/api/v2/catalog...	https://public.opendatasoft.com/api/v2/catalog...	https://public.opendatasoft.com/api/v2/catalog...
XL Picture Url	NaN	https://a0.muscache.com/im/pictures/866cfc5e-f...	https://a0.muscache.com/im/pictures/f13148ba-c...	https://a0.muscache.com/im/pictures/c8acf003-1...	https://a0.muscache.com/im/pictures/ccc118e5-8...
Host ID	76682878	2913511	61647308	5842906	26551999
Host URL	https://www.airbnb.com/users/show/76682878	https://www.airbnb.com/users/show/2913511	https://www.airbnb.com/users/show/61647308	https://www.airbnb.com/users/show/5842906	https://www.airbnb.com/users/show/26551999
Host Name	Hai Wie	Amparo	Carmen Y Ricky	Cristina	Rocio Y Manuel
Host Since	2016-06-09	2012-07-12	2016-03-05	2013-04-09	2015-01-22
Host Location	Madrid, Community of Madrid, Spain	Madrid, Madrid, Spain	Madrid, Community of Madrid, Spain	Madrid, Community of Madrid, Spain	Madrid, Community of Madrid, Spain
Host About	I'm a Chinese-Spanish real estate consultant l...	Soy quien soy por las personas que me rodean y...	NaN	Arqueóloga, investigador postdoctoral y profes...	Somos una pareja de recién casados, muy alegre...
Host Response Time	within a day	within a few hours	within an hour	within an hour	within a few hours
Host Response Rate	70.0	100.0	100.0	100.0	100.0
Host Acceptance Rate	NaN	NaN	NaN	NaN	NaN
Host Thumbnail Url	https://a0.muscache.com/im/pictures/e8de5ad0-6...	https://a0.muscache.com/im/users/2913511/profi...	https://a0.muscache.com/im/pictures/663750d7-f...	https://a0.muscache.com/im/pictures/f0aad32a-2...	https://a0.muscache.com/im/pictures/95c78d4b-5...
Host Picture Url	https://a0.muscache.com/im/pictures/e8de5ad0-6...	https://a0.muscache.com/im/users/2913511/profi...	https://a0.muscache.com/im/pictures/663750d7-f...	https://a0.muscache.com/im/pictures/f0aad32a-2...	https://a0.muscache.com/im/pictures/95c78d4b-5...
Host Neighbourhood	NaN	Usera	Palacio	Embajadores	Malasaña
Host Listings Count	1.0	2.0	1.0	1.0	1.0
Host Total Listings Count	1.0	2.0	1.0	1.0	1.0
Host Verifications	email,phone,reviews	email,phone,reviews,jumio	email,phone,reviews,jumio,government_id	email,phone,facebook	email,phone,reviews,jumio
Street	Madrid, Comunidad de Madrid 28007, Spain	Usera, Madrid, Community of Madrid 28041, Spain	Palacio, Madrid, Comunidad de Madrid 28013, Spain	Embajadores, Madrid, Comunidad de Madrid 28012...	Malasaña, Madrid, Comunidad de Madrid 28015, S...
Neighbourhood	NaN	Usera	Palacio	Embajadores	Malasaña
Neighbourhood Cleansed	Adelfas	San Fermín	Palacio	Embajadores	Universidad
Neighbourhood Group Cleansed	Retiro	Usera	Centro	Centro	Centro
City	Madrid	Madrid	Madrid	Madrid	Madrid
State	Comunidad de Madrid	Community of Madrid	Comunidad de Madrid	Comunidad de Madrid	Comunidad de Madrid
Zipcode	28007.0	28041.0	28013.0	28012.0	28015.0
Market	Madrid	Madrid	Madrid	Madrid	Madrid
Smart Location	Madrid, Spain	Madrid, Spain	Madrid, Spain	Madrid, Spain	Madrid, Spain
Country Code	ES	ES	ES	ES	ES
Country	Spain	Spain	Spain	Spain	Spain
Latitude	40.404759	40.366693	40.422478	40.407975	40.426449
Longitude	-3.669628	-3.687317	-3.710156	-3.698652	-3.712392
Property Type	Apartment	Apartment	Apartment	House	Apartment
Room Type	Private room	Private room	Entire home/apt	Private room	Private room
Accommodates	2	1	4	2	2
Bathrooms	2.0	2.0	1.0	1.0	2.0
Bedrooms	1.0	1.0	1.0	1.0	1.0
Beds	1.0	1.0	2.0	1.0	2.0
Bed Type	Real Bed	Real Bed	Real Bed	Real Bed	Real Bed
Amenities	TV,Wireless Internet,Air conditioning,Pool,Kit...	TV,Wireless Internet,Wheelchair accessible,Kit...	TV,Wireless Internet,Air conditioning,Kitchen,...	TV,Internet,Wireless Internet,Kitchen,Pets all...	Internet,Wireless Internet,Air conditioning,Wh...
Square Feet	NaN	NaN	NaN	NaN	NaN
Price	42.0	30.0	63.0	35.0	34.0
Weekly Price	NaN	170.0	NaN	NaN	NaN
Monthly Price	NaN	500.0	NaN	NaN	NaN
Security Deposit	300.0	NaN	100.0	NaN	NaN
Cleaning Fee	12.0	NaN	NaN	NaN	NaN
Guests Included	1	1	2	1	1
Extra People	0	30	10	10	5
Minimum Nights	2	2	2	1	2
Maximum Nights	1125	1125	1125	3	10
Calendar Updated	4 days ago	2 weeks ago	3 months ago	4 days ago	today
Has Availability	NaN	NaN	NaN	NaN	NaN
Availability 30	11	29	3	20	17
Availability 60	41	51	9	50	33
Availability 90	71	77	18	74	58
Availability 365	71	350	293	74	58
Calendar last Scraped	2017-04-08	2017-04-08	2017-04-07	2017-04-08	2017-04-08
Number of Reviews	4	14	81	4	62
First Review	2016-06-13	2014-05-12	2016-03-14	2017-02-12	2015-11-17
Last Review	2016-10-31	2017-02-12	2017-03-30	2017-04-02	2017-04-05
Review Scores Rating	93.0	94.0	95.0	100.0	96.0
Review Scores Accuracy	9.0	10.0	10.0	10.0	10.0
Review Scores Cleanliness	8.0	10.0	10.0	10.0	10.0
Review Scores Checkin	10.0	9.0	10.0	10.0	10.0
Review Scores Communication	10.0	10.0	10.0	10.0	10.0
Review Scores Location	9.0	9.0	10.0	10.0	10.0
Review Scores Value	9.0	9.0	10.0	10.0	10.0
License	NaN	NaN	NaN	NaN	NaN
Jurisdiction Names	NaN	NaN	NaN	NaN	NaN
Cancellation Policy	moderate	moderate	moderate	flexible	moderate
Calculated host listings count	1.0	2.0	1.0	1.0	1.0
Reviews per Month	0.4	0.4	6.21	2.14	3.65
Geolocation	40.4047594303,-3.66962841278	40.366693238,-3.68731740216	40.42247797,-3.71015640446	40.407974965,-3.69865192241	40.4264486151,-3.7123924029
Features	Host Has Profile Pic,Requires License	Host Has Profile Pic,Host Identity Verified,Is...	Host Has Profile Pic,Host Identity Verified,Is...	Host Has Profile Pic,Is Location Exact,Require...	Host Has Profile Pic,Host Identity Verified,Is...

	ID	Scrape ID	Host ID	Host Response Rate	Host Acceptance Rate	Host Listings Count	Host Total Listings Count	Zipcode	Latitude	Longitude	Accommodates	Bathrooms	Bedrooms	Beds	Square Feet	Price	Weekly Price	Monthly Price	Security Deposit	Cleaning Fee	Guests Included	Extra People	Minimum Nights	Maximum Nights	Has Availability	Availability 30	Availability 60	Availability 90	Availability 365	Number of Reviews	Review Scores Rating	Review Scores Accuracy	Review Scores Cleanliness	Review Scores Checkin	Review Scores Communication	Review Scores Location	Review Scores Value	Jurisdiction Names	Calculated host listings count	Reviews per Month
count	1.060900e+04	1.060900e+04	1.060900e+04	9292.000000	0.0	10607.000000	10607.000000	10252.000000	10609.000000	10609.000000	10609.000000	10571.000000	10595.000000	10576.000000	408.000000	10601.000000	2707.000000	2660.000000	4538.000000	6262.000000	10609.000000	10609.000000	10609.000000	10609.000000	0.0	10609.000000	10609.000000	10609.000000	10609.000000	10609.000000	8325.00000	8312.000000	8316.000000	8302.000000	8314.000000	8300.000000	8299.000000	0.0	10609.000000	8419.000000
mean	1.040110e+07	2.017041e+13	3.750421e+07	94.870319	NaN	9.807674	9.807674	28015.454936	40.420452	-3.697172	3.187859	1.256409	1.293535	1.989883	350.269608	65.693708	368.510528	1334.361654	182.956148	29.681731	1.575832	7.494392	3.014045	980.265906	NaN	8.673862	22.770384	39.874729	205.858799	23.278443	91.61958	9.404475	9.326359	9.620453	9.644215	9.545301	9.214002	NaN	7.661891	1.945315
std	5.496576e+06	4.347861e+00	3.445434e+07	15.140439	NaN	27.624553	27.624553	20.158532	0.020082	0.023733	1.996570	0.611445	0.831415	1.531881	499.223019	56.138300	190.596962	886.872846	107.625972	26.062273	1.081050	10.873778	12.840494	9908.895741	NaN	9.033276	19.406728	29.213100	126.815462	38.482792	8.93289	0.923767	0.984319	0.788198	0.760949	0.754787	0.944337	NaN	19.746585	1.905967
min	1.862800e+04	2.017041e+13	1.745300e+04	0.000000	NaN	0.000000	0.000000	28001.000000	40.331888	-3.863907	1.000000	0.000000	0.000000	1.000000	0.000000	9.000000	70.000000	250.000000	70.000000	4.000000	1.000000	0.000000	1.000000	1.000000	NaN	0.000000	0.000000	0.000000	0.000000	0.000000	20.00000	2.000000	2.000000	2.000000	2.000000	2.000000	2.000000	NaN	1.000000	0.020000
25%	5.820149e+06	2.017041e+13	7.823688e+06	100.000000	NaN	1.000000	1.000000	28005.000000	40.410002	-3.707759	2.000000	1.000000	1.000000	1.000000	0.000000	30.000000	200.000000	700.000000	100.000000	15.000000	1.000000	0.000000	1.000000	365.000000	NaN	0.000000	5.000000	13.000000	84.000000	1.000000	89.00000	9.000000	9.000000	9.000000	9.000000	9.000000	9.000000	NaN	1.000000	0.480000
50%	1.154498e+07	2.017041e+13	2.746121e+07	100.000000	NaN	2.000000	2.000000	28012.000000	40.418568	-3.701573	2.000000	1.000000	1.000000	2.000000	86.000000	52.000000	350.000000	1200.000000	150.000000	25.000000	1.000000	5.000000	2.000000	1125.000000	NaN	6.000000	20.000000	38.000000	247.000000	8.000000	94.00000	10.000000	10.000000	10.000000	10.000000	10.000000	9.000000	NaN	2.000000	1.300000
75%	1.532662e+07	2.017041e+13	5.763190e+07	100.000000	NaN	5.000000	5.000000	28017.000000	40.427649	-3.693854	4.000000	1.000000	2.000000	2.000000	592.000000	80.000000	490.000000	1666.000000	200.000000	35.000000	2.000000	15.000000	3.000000	1125.000000	NaN	13.000000	37.000000	65.000000	321.000000	28.000000	98.00000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	NaN	4.000000	2.910000
max	1.810984e+07	2.017041e+13	1.247534e+08	100.000000	NaN	265.000000	265.000000	28850.000000	40.562736	-3.526821	16.000000	8.000000	10.000000	16.000000	2691.000000	875.000000	995.000000	6990.000000	990.000000	500.000000	15.000000	276.000000	1125.000000	1000000.000000	NaN	30.000000	60.000000	90.000000	365.000000	446.000000	100.00000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	NaN	145.000000	17.210000

	City	State	Country Code	Country
count	10608	10572	10609	10609
unique	19	15	1	1
top	Madrid	Comunidad de Madrid	ES	Spain
freq	10565	8520	10609	10609

	Extra People	Property Type	Price	Bedrooms	Bathrooms	Beds	Neighbourhood Cleansed
2495	276	Apartment	55.0	1.0	1.5	1.0	Trafalgar
4997	250	Chalet	NaN	3.0	3.0	3.0	Niño Jesús
5014	150	Apartment	120.0	1.0	1.0	2.0	Universidad
5591	250	House	NaN	3.0	3.0	3.0	Niño Jesús
8646	274	Apartment	75.0	1.0	1.0	1.0	Universidad
10466	250	Apartment	500.0	1.0	1.0	3.0	Embajadores

Práctica Machine Learning¶

1. Preparación de los datos. División en train y test¶

Filtrar el DataFrame para incluir solamente los registros de Madrid¶

Limpiar Códigos Postales¶

Dividir en train y test¶

2. Análisis Exploratorio¶

Número de Valores Faltantes por Columna¶

Visualización Histogramas¶

Análisis inicial de la correlación¶

Analizando el Dataset por Grupos¶

1. Datos relacionados con la información del anfitrión¶

Conclusiones¶

2. Datos relacionados con la información geográfica¶

Conclusiones¶

3. Características directas del alojamiento¶

Conclusiones¶

4. Datos relacionados con la información de precios y costos adicionales¶

Conclusiones¶

5. Datos relacionados con las restricciones de reserva y la disponibilidad¶

Conclusiones¶

6. Datos relacionados con métricas de calidad y popularidad¶

Conclusiones¶

Outliers¶

Correlación entre variables¶

3. Preprocesamiento¶

Añadir nuevas variables¶

Filtros aplicados en el análisis¶

Primera Eliminación de Características¶

Codificación de características de texto o categóricas¶

Limpiar datos¶

Escalado de características y transformación¶

4. Modelado¶

Aplicar las mismas transformaciones que en train¶

Definir una función para calcular múltiples métricas¶

Selección de Características - Lasso¶

Linear Regression¶

Árbol de Decisión (DecisionTreeRegressor)¶

Random Forest¶

Bagging Regressor¶

Gradient Boosting Regressor¶

SVMs¶

Kernel Ridge Regression¶

Comparando modelos¶

5. Conclusión¶